欢迎来到网际学院,让您的头脑满载而归!

CVPR2019 全部论文开源代码

发布日期:2020-05-01 21:08:51 作者:管理员 阅读:238

Notitlegithub/codepaper reading articleproject linkCatorgoryOral dayOral sessionOral timePoster dayPoster sessionPoster


Notitlegithub/codepaper reading articleproject linkCatorgoryOral dayOral sessionOral timePoster dayPoster sessionPoster #First authorAuthor

304A Simple Pooling-Based Design for Real-Time Salient Object Detectionhttp://mmcheng.net/poolnet/





TuesdayPoster 1.2163Jiang-Jiang LiuJiang-Jiang Liu, Qibin Hou, Ming-Ming Cheng, Jiashi Feng, Jianmin Jiang

305DeepMapping: Unsupervised Map Estimation From Multiple Point Cloudshttps://ai4ce.github.io/DeepMapping/


ThursdayOral 3.1A9:47ThursdayPoster 3.1203Li DingLi Ding, Chen Feng

306Action Recognition From Single Timestamp Supervision in Untrimmed Videoshttps://bitbucket.org/dmoltisanti/action_recognition_single_timestamps/src/master/
https://dimadamen.github.io/single_timestamps/



ThursdayPoster 3.1129Davide MoltisantiDavide Moltisanti, Sanja Fidler, Dima Damen

307FilterReg: Robust and Efficient Probabilistic Point-Set Registration Using Gaussian Filter and Twist Parameterizationhttps://bitbucket.org/gaowei19951004/poser/src/master/


ThursdayOral 3.2C14:34ThursdayPoster 3.2158Wei GaoWei Gao, Russ Tedrake

117Unsupervised Deep Trackinghttps://github.com/594422814/UDT





TuesdayPoster 1.1132Ning WangNing Wang, Yibing Song, Chao Ma, Wengang Zhou, Wei Liu, Houqiang Li

308Social-IQ: A Question Answering Benchmark for Artificial Social Intelligencehttps://github.com/A2Zadeh/Social-IQ


ThursdayOral 3.1B9:52ThursdayPoster 3.191Amir Zadeh

1059All About Structure: Adapting Structural Information Across Domains for Boosting Semantic Segmentationhttps://github.com/a514514772/DISE-Domain-Invariant-Structure-Extraction





TuesdayPoster 1.1192Wei-Lun Chang

309Reflection Removal Using a Dual-Pixel Sensorhttps://github.com/abhijithpunnappurath/dprr
https://abhijithpunnappurath.github.io/dprr



TuesdayPoster 1.1157Abhijith PunnappurathAbhijith Punnappurath ,Michael S. Brown

261Art2Real: Unfolding the Reality of Artworks via Semantically-Aware Image-To-Image Translationhttps://github.com/aimagelab/art2real





WednesdayPoster 2.1161Matteo TomeiMatteo Tomei, Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

150Latent Space Autoregression for Novelty Detectionhttps://github.com/aimagelab/novelty-detection





TuesdayPoster 1.125Davide AbatiDavide Abati, Angelo Porrello, Simone Calderara, Rita Cucchiara

96Show, Control and Tell: A Framework for Generating Controllable and Grounded Captionshttps://github.com/aimagelab/show-control-and-tell





WednesdayPoster 2.2195Marcella CorniaMarcella Cornia, Lorenzo Baraldi, Rita Cucchiara

123Strike (With) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objectshttps://github.com/airalcorn2/strike-with-a-pose





WednesdayPoster 2.129Michael A. AlcornMichael A. Alcorn, Qi Li, Zhitao Gong, Chengfei Wang, Long Mai, Wei-Shinn Ku, Anh Nguyen

310Learning 3D Human Dynamics From Videohttps://github.com/akanazawa/human_dynamics?





WednesdayPoster 2.1122Angjoo KanazawaAngjoo Kanazawa, Jason Y. Zhang, Panna Felsen, Jitendra Malik

311Video Action Transformer Networkhttps://github.com/alainray/action_transformer


TuesdayOral 1.1C9:00TuesdayPoster 1.1109Rohit GirdharRohit Girdhar, Jo?o Carreira, Carl Doersch, Andrew Zisserman

312Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Predictionhttps://github.com/alexklwong/adareg-monodispnet





WednesdayPoster 2.1125Alex WongAlex Wong, Byung-Woo Hong, Stefano Soatto

81Animating Arbitrary Objects via Deep Motion Transferhttps://github.com/AliaksandrSiarohin/monkey-net


TuesdayOral 1.2B14:06TuesdayPoster 1.2124Aliaksandr SiarohinAliaksandr Siarohin,?Stéphane Lathuilière,?Sergey Tulyakov,?Elisa Ricci,?Nicu Sebe

194ELASTIC: Improving CNNs With Dynamic Scaling Policieshttps://github.com/allenai/elastic


TuesdayOral 1.2A14:42TuesdayPoster 1.230Huiyu WangHuiyu Wang, Aniruddha Kembhavi, Ali Farhadi, Alan Yuille, Mohammad Rastegari

129Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learninghttps://github.com/allenai/savn


WednesdayOral 2.2B15:10WednesdayPoster 2.2194Mitchell WortsmanMitchell Wortsman, Kiana Ehsani, Mohammad Rastegari, Ali Farhadi, Roozbeh Mottaghi

636Argoverse: 3D Tracking and Forecasting With Rich Mapshttps://github.com/alliecc/argoverse_baselinetracker


ThursdayOral 3.1B9:16ThursdayPoster 3.185Ming-Fang Chang

59Recurrent Back-Projection Network for Video Super-Resolutionhttps://github.com/alterzero/RBPN-PyTorch
https://alterzero.github.io/projects/RBPN.html



TuesdayPoster 1.2161Muhammad HarisMuhammad Haris, Greg Shakhnarovich, Norimichi Ukita?

242Trust Region Based Adversarial Attack on Neural Networkshttps://github.com/amirgholami/trattack





ThursdayPoster 3.238Zhewei YaoZhewei Yao, Amir Gholami, Peng Xu, Kurt Keutzer, Michael Mahoney

313GPSfM: Global Projective SFM Using Algebraic Constraints on Multi-View Fundamental Matriceshttps://github.com/amnonge/GPSFM-Code





TuesdayPoster 1.279Yoni KastenYoni Kasten* Amnon Geifman* Meirav Galun Ronen Basri

314Depth From a Polarisation + RGB Stereo Pairhttps://github.com/AmosZhu/CVPR2019





WednesdayPoster 2.286Dizhong ZhuDizhong Zhu, William A.P. Smith

315Improved Road Connectivity by Joint Learning of Orientation and Segmentationhttps://github.com/anilbatra2185/road_connectivity





ThursdayPoster 3.1177Anil BatraAnil Batra,Suriya Singh,Guan Pang,Saikat Basu,C.V. Jawahar1 Manohar Paluri

162Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image Retrievalhttps://github.com/AnjanDutta/sem-pcyc





WednesdayPoster 2.154Anjan DuttaAnjan Dutta, Zeynep Akata

205Unsupervised Learning of Action Classes With Continuous Temporal Embeddinghttps://github.com/annusha/unsup_temp_embed





ThursdayPoster 3.2129Anna KuklevaAnna Kukleva, Hilde Kuehne, Fadime Sener, Juergen Gall

316Bringing Alive Blurred Momentshttps://github.com/anshulbshah/Blurred-Image-to-Video


WednesdayOral 2.2C14:11WednesdayPoster 2.2137Kuldeep Purohit

55Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentationhttps://github.com/anuragranj/cc





ThursdayPoster 3.2165Anurag RanjanAnurag Ranjan, Varun Jampani, Lukas Balles, Kihwan Kim, Deqing Sun, Jonas Wulff, Michael J. Black?

317Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptationhttps://github.com/apple/ml-cvpr2019-swd





ThursdayPoster 3.1167Chen-Yu LeeChen-Yu Lee, Tanmay Batra, Mohammad Haris Baig, Daniel Ulbricht

747Attentive Feedback Network for Boundary-Aware Salient Object Detectionhttps://github.com/ArcherFMY/AFNet





TuesdayPoster 1.1164Mengyang Feng

1224Viewport Proposal CNN for 360deg Video Quality Assessmenthttps://github.com/Archer-Tatsu/V-CNN





ThursdayPoster 3.1156Chen Li

318Zero-Shot Task Transferhttps://github.com/ArghyaPal/Zero-shot-task-transfer


TuesdayOral 1.2A13:58TuesdayPoster 1.223Arghya Pal

282A-CNN: Annularly Convolutional Neural Networks on Point Cloudshttps://github.com/artemkomarichev/a-cnn





WednesdayPoster 2.269Artem KomarichevArtem Komarichev, Zichun Zhong, Jing Hua

319Automatic Adaptation of Object Detectors to New Domains Using Self-Traininghttps://github.com/AruniRC/detectron-self-train
http://vis-www.cs.umass.edu/self-train/



TuesdayPoster 1.155Aruni RoyChowdhuryAruni RoyChowdhury, Prithvijit Chakrabarty, Ashish Singh, SouYoung Jin, Huaizu Jiang, Liangliang Cao and Erik Learned-Miller

320PointFlowNet: Learning Representations for Rigid Motion Estimation From Point Cloudshttps://github.com/aseembehl/pointflownet





WednesdayPoster 2.2124Aseem BehlAseem Behl, Despoina Paschalidou, Simon Donné, Andreas Geiger

321LAEO-Net: Revisiting People Looking at Each Other in Videoshttps://github.com/AVAuco/ucolaeodb
http://www.robots.ox.ac.uk/~vgg/research/laeonet?



TuesdayPoster 1.2100Manuel J. Marin-JimenezManuel J Marin-Jimenez,Vicky Kalogeiton,Pablo Medina-Suarez,Andrew Zisserman

239Noise-Aware Unsupervised Deep Lidar-Stereo Fusionhttps://github.com/AvrilCheng/LidarStereoNet





WednesdayPoster 2.1211Xuelian ChengXuelian Cheng, Yiran Zhong, Yuchao Dai, Pan Ji, Hongdong Li

322Handwriting Recognition in Low-Resource Scripts Using Adversarial Learninghttps://github.com/AyanKumarBhunia/Handwriting_Recogition_using_Adversarial_Learning?





WednesdayPoster 2.121Ayan Kumar BhuniaAyan Kumar Bhunia, Abhirup Das, Ankan Kumar Bhunia, Perla Sai Raj Kishore, Partha Pratim Roy

92Depth-Aware Video Frame Interpolationhttps://github.com/baowenbo/DAIN





TuesdayPoster 1.2141Wenbo BaoWenbo Bao Wei-Sheng Lai, Chao Ma, Xiaoyun Zhang, Zhiyong Gao, and Ming-Hsuan Yang

69GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstructionhttps://github.com/barisgecer/ganfit





TuesdayPoster 1.1105Baris GecerBaris Gecer, Stylianos Ploumpis, Irene Kotsia, Stefanos Zafeiriou

323RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimationhttps://github.com/bastianwandt/RepNet





WednesdayPoster 2.2106Bastian WandtBastian Wandt, Bodo Rosenhahn

324End-To-End Projector Photometric Compensationhttps://github.com/BingyaoHuang/compennet?


WednesdayOral 2.2C13:58WednesdayPoster 2.2135Bingyao HuangBingyao Huang, Haibin Ling

185A Poisson-Gaussian Denoising Dataset With Real Fluorescence Microscopy Imageshttps://github.com/bmmi/denoising-fluorescence





ThursdayPoster 3.275Yide ZhangYide Zhang, Yinhao Zhu, Evan Nichols, Qingfei Wang, Siyuan Zhang, Cody Smith, Scott Howard

184Deep RNN Framework for Visual Sequential Applicationshttps://github.com/BoPang1996/Deep-RNN-Framework





TuesdayPoster 1.119Bo PangBo Pang, Kaiwen Zha, Hanwen Cao, Chen Shi, Cewu Lu

3253D Hand Shape and Pose From Images in the Wildhttps://github.com/boukhayma/3dhand


ThursdayOral 3.2B13:53ThursdayPoster 3.296Adnane BoukhaymaAdnane Boukhayma, Rodrigo de Bem, Philip H.S. Torr

151DeepCaps: Going Deeper With Capsule Networkshttps://github.com/brjathu/deepcaps


ThursdayOral 3.2A14:29ThursdayPoster 3.211Jathushan RajasegaranJathushan Rajasegaran, Vinoj Jayasundara, Sandaru Jayasekara, Hirunima Jayasekara, Suranga Seneviratne, Ranga Rodrigo

84MUREL: Multimodal Relational Reasoning for Visual Question Answeringhttps://github.com/Cadene/murel.bootstrap.pytorchhttps://zhuanlan.zhihu.com/p/60972299




TuesdayPoster 1.1201Remi CadeneRemi Cadene, Hedi Ben-younes, Matthieu Cord, Nicolas Thome

326Pyramid Feature Attention Network for Saliency Detectionhttps://github.com/CaitinZhao/cvpr2019_Pyramid-Feature-Attention-Network-for-Saliency-detection





TuesdayPoster 1.261Ting ZhaoTing Zhao, Xiangqian Wu

902See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networkshttps://github.com/carrierlxk/COSNet





TuesdayPoster 1.2115Xiankai Lu

327Zoom to Learn, Learn to Zoomhttps://github.com/ceciliavision/zoom-learn-zoom
https://ceciliavision.github.io/project-pages/project-zoom.html?



TuesdayPoster 1.2147Xuaner ZhangXuaner Cecilia Zhang, Qifeng Chen, Ren Ng, Vladlen Koltun

206Generating Multiple Hypotheses for 3D Human Pose Estimation With Mixture Density Networkhttps://github.com/chaneyddtt/Generating-Multiple-Hypotheses-for-3D-Human-Pose-Estimation-with-Mixture-Density-Network





ThursdayPoster 3.1126Chen LiChen Li, Gim Hee Lee

328Hybrid-Attention Based Decoupled Metric Learning for Zero-Shot Image Retrievalhttps://github.com/chenbinghui1/Hybrid-Attention-based-Decoupled-Metric-Learning?





TuesdayPoster 1.29Binghui ChenBinghui Chen, Weihong Deng

82Photometric Mesh Optimization for Video-Aligned 3D Object Reconstructionhttps://github.com/chenhsuanlin/photometric-mesh-optim
https://chenhsuanlin.bitbucket.io/photometric-mesh-optim/



TuesdayPoster 1.186Chen-Hsuan LinPelin Dogan, Leonid Sigal, Markus Gross

118Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Imageshttps://github.com/chenwydj/ultra_high_resolution_segmentation


ThursdayOral 3.1C9:34ThursdayPoster 3.166Wuyang ChenWuyang Chen, Ziyu Jiang, Zhangyang Wang, Kexin Cui, Xiaoning Qian

329Fully Automatic Video Colorization With Self-Regularization and Diversityhttps://github.com/ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity





TuesdayPoster 1.2146Chenyang Lei

330Multi-Label Image Recognition With Graph Convolutional Networkshttps://github.com/chenzhaomin123/ML_GCN





WednesdayPoster 2.163Zhao-Min ChenZhao-Min Chen, Xiu-Shen Wei, Peng Wang, Yanwen Guo

80Learning Attraction Field Representation for Robust Line Segment Detectionhttps://github.com/cherubicXN/afm_cvpr2019





TuesdayPoster 1.1161Nan XueNan Xue,?Song Bai,?Fudong Wang,?Gui-Song Xia,?Tianfu Wu,?Liangpei Zhang

101The Regretful Agent: Heuristic-Aided Navigation Through Progress Estimationhttps://github.com/chihyaoma/regretful-agent


WednesdayOral 2.2B15:00WednesdayPoster 2.2192Chih-Yao MaChih-Yao Ma, Zuxuan Wu, Ghassan AlRegib, Caiming Xiong, Zsolt Kira

262Iterative Residual CNNs for Burst Photography Applicationshttps://github.com/cig-skoltech/burst-cvpr-2019





WednesdayPoster 2.1169Filippos KokkinosFilippos Kokkinos ? Stamatis Lefkimmiatis

119Improving Transferability of Adversarial Examples With Input Diversityhttps://github.com/cihangxie/DI-2-FGSM





TuesdayPoster 1.27Cihang XieCihang Xie; Yuyin Zhou; Song Bai; Zhishuai Zhang; Jianyu Wang; Zhou Ren; Alan Yuille

132TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environmentshttps://github.com/clic-lab/touchdown





ThursdayPoster 3.2195Howard ChenHoward Chen, Alane Suhr, Dipendra Misra, Noah Snavely, Yoav Artzi

679Character Region Awareness for Text Detectionhttps://github.com/clovaai/CRAFT-pytorch





ThursdayPoster 3.143Youngmin Baek

563Monocular Total Capture: Posing Face, Body, and Hands in the Wildhttps://github.com/CMU-Perceptual-Computing-Lab/MonocularTotalCapture
http://domedb.perception.cs.cmu.edu/monototalcapture.html
ThursdayOral 3.2B15:05ThursdayPoster 3.2108Donglai XiangDonglai Xiang, Hanbyul Joo, Yaser Sheikh

68Panoptic Segmentationhttps://github.com/cocodataset/panopticapi





ThursdayPoster 3.147Alexander KirillovHuanyu Liu, Chao Peng, Changqian Yu, Jingbo Wang, Xu Liu, Gang Yu, Wei Jiang

331Towards Natural and Accurate Future Motion Prediction of Humans and Animalshttps://github.com/CoderStellaJ/Hierarchical-Motion-Recurrent-Network-Websitehttps://coderstellaj.github.io/Hierarchical-Motion-Recurrent-Network-Website/




ThursdayPoster 3.1138Zhenguang LiuZhenguang Liu (Zhejiang Gongshang University)*; Shuang Wu (Nanyang Technological University); Shuyuan Jin (NUS); Qi Liu (National University of Singapore); Shijian Lu (Nanyang Technological University); Roger Zimmermann (NUS); Li Cheng (University of Alberta)

1067Deep Defocus Map Estimation Using Domain Adaptationhttps://github.com/codeslake/SYNDOF





ThursdayPoster 3.2145Junyong Lee

332COIN: A Large-Scale Dataset for Comprehensive Instructional Video Analysishttps://github.com/coin-dataset/codehttps://mp.weixin.qq.com/s/YFmgdIEfLCvL5LLGQ0veswhttps://coin-dataset.github.io/



TuesdayPoster 1.1122Yansong TangYansong Tang, Dajun Ding, Yongming Rao, Yu Zheng, Danyang Zhang, Lili Zhao, Jiwen Lu, Jie Zhou

333Context-Aware Crowd Countinghttps://github.com/CommissarMa/Context-Aware_Crowd_Counting-pytorch





WednesdayPoster 2.155Weizhe LiuWeizhe Liu, Mathieu Salzmann, Pascal Fua

334Acoustic Non-Line-Of-Sight Imaginghttps://github.com/computational-imaging/AcousticNLOS
http://www.computationalimaging.org/publications/acoustic-non-line-of-sight-imaging/
WednesdayOral 2.2C13:40WednesdayPoster 2.2132David B. LindellDavid B. Lindell, Gordon Wetzstein, Vladlen Koltun

335Divide and Conquer the Embedding Space for Metric Learninghttps://github.com/CompVis/metric-learning-divide-and-conquer





TuesdayPoster 1.124Artsiom SanakoyeuSanakoyeu, Artsiom and Tschernezki, Vadim and B\"uchler, Uta and Ommer, Bj\"orn

1277A Neural Temporal Model for Human Motion Predictionhttps://github.com/cr7anand/neural_temporal_models





ThursdayPoster 3.2134Anand Gopalakrishnan

130Progressive Image Deraining Networks: A Better and Simpler Baselinehttps://github.com/csdwren/PReNet





TuesdayPoster 1.2165Dongwei RenDongwei Ren, Wangmeng Zuo, Qinghua Hu, Pengfei Zhu, Deyu Meng

186Supervised Fitting of Geometric Primitives to 3D Point Cloudshttps://github.com/csimstu2/SPFN


TuesdayOral 1.2C15:05TuesdayPoster 1.2182Lingxiao LiLingxiao Li, Minhyuk Sung, Anastasia Dubrovina, Li Yi, Leonidas Guibas

336STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editinghttps://github.com/csmliu/STGAN?





TuesdayPoster 1.2138Ming LiuMing Liu, Yukang Ding, Min Xia, Xiao Liu, Errui Ding, Wangmeng Zuo, Shilei Wen

28Deep Plug-And-Play Super-Resolution for Arbitrary Blur Kernelshttps://github.com/cszn/DPSR





TuesdayPoster 1.1169Kai ZhangKai Zhang, Wangmeng Zuo, Lei Zhang

192Segmentation-Driven 6D Object Pose Estimationhttps://github.com/cvlab-epfl/segmentation-driven-pose





TuesdayPoster 1.291Yinlin HuYinlin Hu, Joachim Hugonot, Pascal Fua, Mathieu Salzmann

179Learning to Adapt for Stereohttps://github.com/CVLAB-Unibo/Learning2AdaptForStereo





ThursdayPoster 3.1103Alessio TonioniAlessio Tonioni, Oscar Rahnama, Thomas Joy, Luigi Di Stefano, Thalaiyasingam Ajanthan, Philip H. S. Torr

76Real-Time Self-Adaptive Deep Stereohttps://github.com/CVLAB-Unibo/Real-time-self-adaptive-deep-stereo


TuesdayOral 1.1B9:41TuesdayPoster 1.179Alessio TonioniAlessio Tonioni, Fabio Tosi, Matteo Poggi, Stefano Mattoccia, Luigi Di Stefano?

337Example-Guided Style-Consistent Image Synthesis From Semantic Labelinghttps://github.com/cxjyxxme/pix2pixSC





TuesdayPoster 1.1151Miao WangMiao Wang1, Guo-Ye Yang2, Ruilong Li2, Run-Ze Liang2, Song-Hai Zhang2, Peter M. Hall3?and Shi-Min Hu

62Rethinking Knowledge Graph Propagation for Zero-Shot Learninghttps://github.com/cyvius96/adgpm





ThursdayPoster 3.252Michael KampffmeyerMichael Kampffmeyer, Yinbo Chen, Xiaodan Liang, Hao Wang, Yujia Zhang, Eric P. Xing

56Learning Implicit Fields for Generative Shape Modelinghttps://github.com/czq142857/implicit-decoder?





WednesdayPoster 2.1170Zhiqin ChenZhiqin Chen, Hao Zhang

14PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understandinghttps://github.com/daerduoCarey/partnet_dataset
https://cs.stanford.edu/~kaichun/partnet/



TuesdayPoster 1.168Kaichun MoKaichun Mo, Shilin Zhu, Angel X. Chang, Li Yi, Subarna Tripathi, Leonidas J. Guibas, Hao Su

338Visual Tracking via Adaptive Spatially-Regularized Correlation Filtershttps://github.com/Daikenan/ASRCF


WednesdayOral 2.1C9:29WednesdayPoster 2.1145Kenan DaiKenan Dai, Dong Wang, Huchuan Lu, Chong Sun, Jianhua Li

339Second-Order Attention Network for Single Image Super-Resolutionhttps://github.com/daitao/SAN


ThursdayOral 3.2C14:16ThursdayPoster 3.2155Tao Dai

340Dual Encoding for Zero-Example Video Retrievalhttps://github.com/danieljf24/dual_encoding





ThursdayPoster 3.141Jianfeng DongJianfeng Dong, Xirong Li, Chaoxi Xu, Shouling Ji, Yuan He, Gang Yang and Xun Wang

341MAGSAC: Marginalizing Sample Consensushttps://github.com/danini/magsac





ThursdayPoster 3.1158Daniel Barath

957Disentangling Adversarial Robustness and Generalizationhttps://github.com/davidstutz/cvpr2019-adversarial-robustness





WednesdayPoster 2.25David Stutz

512Few-Shot Learning With Localization in Realistic Settingshttps://github.com/daviswer/fewshotlocal


WednesdayOral 2.2A15:05WednesdayPoster 2.241Davis Wertheimer

231Vision-Based Navigation With Language-Based Assistance via Imitation Learning With Indirect Interventionhttps://github.com/debadeepta/vnla





ThursdayPoster 3.2194Khanh NguyenKhanh Nguyen, Debadeepta Dey, Chris Brockett, Bill Dolan

15ABC: A Big CAD Model Dataset for Geometric Deep Learninghttps://github.com/deep-geometry/abc-dataset?





ThursdayPoster 3.197Sebastian KochSebastian Koch, Albert Matveev, Zhongshi Jiang, Francis Williams, Alexey Artemov, Evgeny Burnaev, Marc Alexa, Denis Zorin, Daniele Panozzo

4ArcFace: Additive Angular Margin Loss for Deep Face Recognitionhttps://github.com/deepinsight/insightface


WednesdayOral 2.1C9:42WednesdayPoster 2.1147Jiankang DengJiankang Deng, Jia Guo, Niannan Xue, Stefanos Zafeiriou

342Exploiting Temporal Context for 3D Human Pose Estimation in the Wildhttps://github.com/deepmind/Temporal-3D-Pose-Kinetics?





TuesdayPoster 1.292Anurag ArnabAnurag Arnab, Carl Doersch, Andrew Zisserman

343Shifting More Attention to Video Salient Object Detectionhttps://github.com/DengPingFan/DAVSOD


ThursdayOral 3.1A8:48ThursdayPoster 3.1193Deng-Ping FanDeng-Ping Fan, Wenguan Wang, Ming-Ming Cheng, Jianbing Shen

144Transferable Interactiveness Knowledge for Human-Object Interaction Detectionhttps://github.com/DirtyHarryLYL/Transferable-Interactiveness-Network





TuesdayPoster 1.2111Yong-Lu LiYong-Lu Li, Siyuan Zhou, Xijie Huang, Liang Xu, Ze Ma, Hao-Shu Fang, Yan-Feng Wang, Cewu Lu

293Beyond Gradient Descent for Regularized Segmentation Losseshttps://github.com/dmitrii-marin/adm-seg





ThursdayPoster 3.1157Dmitrii MarinDmitrii Marin, Meng Tang, Ismail Ben Ayed, Yuri Boykov

6Bag of Tricks for Image Classification with Convolutional Neural Networkshttps://github.com/dmlc/gluon-cv





TuesdayPoster 1.133Tong HeTong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li

251Cross-Task Weakly Supervised Learning From Instructional Videoshttps://github.com/DmZhukov/CrossTask





TuesdayPoster 1.2106Dimitri ZhukovDimitri Zhukov, Jean-Baptiste Alayrac, Ramazan Gokberk Cinbis, David Fouhey, Ivan Laptev, Josef Sivic

207LiFF: Light Field Features in Scale and Depthhttps://github.com/doda42/LiFF





WednesdayPoster 2.2150Donald G. DansereauDonald G. Dansereau, Bernd Girod, Gordon Wetzstein

344Dense Relational Captioning: Triple-Stream Networks for Relationship-Based Captioninghttps://github.com/Dong-JinKim/DenseRelationalCaptioning





WednesdayPoster 2.1204Dong-Jin KimDone by Dong-Jin Kim, Jinsoo Choi, Tae-Hyun Oh, and In So Kweon

345Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cellshttps://github.com/DrSleep/nas-segm-pytorch





ThursdayPoster 3.118Vladimir NekrasovVladimir Nekrasov, Hao Chen, Chunhua Shen, Ian Reid

346OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networkshttps://github.com/dsfour/OICSR





WednesdayPoster 2.212Jiashi LiJiashi Li, Qi Qi, Jingyu Wang, Ce Ge, Yujian Li, Zhangzhang Yue, Haifeng Sun

347CrossInfoNet: Multi-Task Information Sharing Based Hand Pose Estimationhttps://github.com/dumyy/handpose





ThursdayPoster 3.1127Kuo DuKuo Du, Xiangbo Lin, Yi Sun, Xiaohong Ma

348Searching for a Robust Neural Architecture in Four GPU Hourshttps://github.com/D-X-Y/GDAS?





TuesdayPoster 1.1178Xuanyi DongXuanyi Dong, Yi Yang

52PointConv: Deep Convolutional Networks on 3D Point Cloudshttps://github.com/DylanWusee/pointconv





ThursdayPoster 3.199Wenxuan WuWenxuan Wu, Zhongang Qi, Li Fuxin

163Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencodershttps://github.com/edgarschnfld/CADA-VAE-PyTorch





WednesdayPoster 2.2171Edgar SchonfeldEdgar Sch?nfeld, Sayna Ebrahimi, Samarth Sinha, Trevor Darrell, Zeynep Akata

43Precise Detection in Densely Packed Sceneshttps://github.com/eg4000/SKU110K_CVPR19





WednesdayPoster 2.168Eran GoldmanEran Goldman , Roei Herzig, Aviv Eisenschtat, Jacob Goldberger, Tal Hassner?

349Mixture Density Generative Adversarial Networkshttps://github.com/eghbalz/mdgan





WednesdayPoster 2.1158Hamid Eghbal-zadehHamid Eghbal-zadeh, Werner Zellinger, Gerhard Widmer

294Exploring the Bounds of the Utility of Context for Object Detectionhttps://github.com/EhudBarnea/ContextAnalysis





WednesdayPoster 2.268Ehud BarneaEhud Barnea, Ohad Ben-Shahar

23Data-Driven Neuron Allocation for Scale Aggregation Networkshttps://github.com/Eli-YiLi/ScaleNet





ThursdayPoster 3.256Yi LiYi Li, Zhanghui Kuang, Yimin Chen, Wayne Zhang

706GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloudhttps://github.com/ericyi/GSPN





TuesdayPoster 1.2184Li Yi

252NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reductionhttps://github.com/ethanygao/NDDR-CNN





TuesdayPoster 1.273Yuan GaoYuan Gao, Jiayi Ma, Mingbo Zhao, Wei Liu, Alan L. Yuille

232DLOW: Domain Flow for Adaptation and Generalizationhttps://github.com/ETHRuiGong/DLOW


TuesdayOral 1.2B15:05TuesdayPoster 1.2134Rui GongRui Gong, Wen Li, Yuhua Chen, Luc Van Gool

145From Coarse to Fine: Robust Hierarchical Localization at Large Scalehttps://github.com/ethz-asl/hf_net





ThursdayPoster 3.2213Paul-Edouard SarlinPaul-Edouard Sarlin, Cesar Cadena, Roland Siegwart, Marcin Dymczyk

269A Local Block Coordinate Descent Algorithm for the CSC Modelhttps://github.com/EvZissel/LoBCoD





WednesdayPoster 2.2167Ev ZisselmanEv Zisselman, Jeremias Sulam, Michael Elad

137Learning Monocular Depth Estimation Infusing Traditional Stereo Knowledgehttps://github.com/fabiotosi92/monoResMatch-Tensorflow





ThursdayPoster 3.1117Fabio TosiFabio Tosi, Filippo Aleotti, Matteo Poggi, Stefano Mattoccia

350Practical Full Resolution Learned Lossless Image Compressionhttps://github.com/fab-jul/L3C-PyTorch


ThursdayOral 3.2A13:30ThursdayPoster 3.21Fabian MentzerFabian Mentzer, Eirikur Agustsson, Michael Tschannen, Radu Timofte, Luc Van Gool

1291Attentive Single-Tasking of Multiple Taskshttps://github.com/facebookresearch/astmt





TuesdayPoster 1.1187Kevis-Kokitsi Maninis

2332.5D Visual Soundhttps://github.com/facebookresearch/FAIR-Play
http://vision.cs.utexas.edu/projects/2.5D_visual_sound/
TuesdayOral 1.1C9:46TuesdayPoster 1.1117Ruohan GaoRuohan Gao, Kristen Grauman

172Grounded Video Descriptionhttps://github.com/facebookresearch/grounded-video-description


WednesdayOral 2.2B13:30WednesdayPoster 2.2177Luowei ZhouLuowei Zhou, Yannis Kalantidis, Xinlei Chen, Jason J. Corso, Marcus Rohrbach

30Feature Denoising for Improving Adversarial Robustnesshttps://github.com/facebookresearch/ImageNet-Adversarial-Training





TuesdayPoster 1.127Cihang XieCihang Xie, Yuxin Wu, Laurens van der Maaten, Alan Yuille, Kaiming He

351Inverse Cooking: Recipe Generation From Food Imageshttps://github.com/facebookresearch/inversecooking





ThursdayPoster 3.1184Amaia SalvadorAmaia Salvador, Michal Drozdzal, Xavier Giro-i-Nieto, Adriana Romero

7Towards VQA Models That Can Readhttps://github.com/facebookresearch/pythia





WednesdayPoster 2.2196Amanpreet SinghAmanpreet Singh, Vivek Natarajan, Meet Shah, Yu Jiang, Xinlei Chen, Dhruv Batra, Devi Parikh, Marcus Rohrbach

193D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Traininghttps://github.com/facebookresearch/VideoPose3D





WednesdayPoster 2.2103Dario PavlloDario Pavllo, Christoph Feichtenhofer, David Grangier, Michael Auli

234Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answeringhttps://github.com/fanchenyou/HME-VideoQA





TuesdayPoster 1.1202Chenyou FanChenyou Fan, Xiaofan Zhang, Shu Zhang, Wensheng Wang, Chi Zhang, Heng Huang

352MVF-Net: Multi-View 3D Face Morphable Model Regressionhttps://github.com/Fanziapril/mvfnet





TuesdayPoster 1.185Fanzi WuFanzi Wu, Linchao Bao, Yajing Chen, Yonggen Ling, Yibing Song, Songnan Li, King Ngi Ngan, Wei Liu

283Learning Not to Learn: Training Deep Neural Networks With Biased Datahttps://github.com/feidfoe/learning-not-to-learn





ThursdayPoster 3.16Byungju KimByungju Kim, Hyunwoo Kim, Kyungsu Kim, Sungjin Kim, Junmo Kim

134GA-Net: Guided Aggregation Net for End-To-End Stereo Matchinghttps://github.com/feihuzhang/GANet


TuesdayOral 1.1B9:36TuesdayPoster 1.178Feihu ZhangFeihu Zhang, Victor Prisacariu, Ruigang Yang, Philip H.S. Torr

526Beyond Tracking: Selecting Memory and Refining Poses for Deep Visual Odometryhttps://github.com/feixue94/BeyondTrcking


ThursdayOral 3.1A8:58ThursdayPoster 3.1195Fei Xue

353Unsupervised Image Captioninghttps://github.com/fengyang0317/unsupervised_captioning?





TuesdayPoster 1.2202Yang FengYang Feng, Lin Ma, Wei Liu, Jiebo Luo

21Fast Interactive Object Annotation With Curve-GCNhttps://github.com/fidler-lab/curve-gcn





WednesdayPoster 2.171Huan LingHuan Ling, Jun Gao, Amlan Kar, Wenzheng Chen, Sanja Fidler?

1105Object-Centric Auto-Encoders and Dummy Anomalies for Abnormal Event Detection in Videohttps://github.com/fjchange/object_centric_VAD





WednesdayPoster 2.2112Radu Tudor Ionescu

817Frame-Consistent Recurrent Video Deraining With Dual-Level Flowhttps://github.com/flyywh/Dual-FLow-Video-Deraining-CVPR-2019





TuesdayPoster 1.1168Wenhan Yang

216Domain Generalization by Solving Jigsaw Puzzleshttps://github.com/fmcarlucci/JigenDG


TuesdayOral 1.2A14:24TuesdayPoster 1.227Fabio M. CarlucciFabio Maria Carlucci, Antonio D'Innocente, Silvia Bucci, Barbara Caputo, Tatiana Tommasi

960ESIR: End-To-End Scene Text Recognition via Iterative Image Rectificationhttps://github.com/fnzhan/ESIR





TuesdayPoster 1.1208Fangneng Zhan

354Spatial Fusion GAN for Image Synthesishttps://github.com/fnzhan/SF-GAN





TuesdayPoster 1.2136Fangneng Zhan

355PartNet: A Recursive Part Decomposition Network for Fine-Grained and Hierarchical Shape Segmentationhttps://github.com/FoggYu/PartNet





ThursdayPoster 3.171Fenggen YuFenggen Yu, Kun Liu, Yan Zhang, Chenyang Zhu, Kai Xu

9Fast Online Object Tracking and Segmentation: A Unifying Approachhttps://github.com/foolwood/SiamMask
http://www.robots.ox.ac.uk/~qwang/SiamMask/



TuesdayPoster 1.1134Qiang WangQiang Wang,?Li Zhang,?Luca Bertinetto,?Weiming Hu,?Philip H.S. Torr

570Revealing Scenes by Inverting Structure From Motion Reconstructionshttps://github.com/francescopittaluga/invsfm


TuesdayOral 1.1B9:10TuesdayPoster 1.174Francesco Pittaluga

243Good News, Everyone! Context Driven Entity-Aware Captioning for News Imageshttps://github.com/furkanbiten/GoodNews





ThursdayPoster 3.2188Ali Furkan BitenAli Furkan Biten, Lluis Gomez, Mar?al Rusi?ol, Dimosthenis Karatzas

356Deep Geometric Prior for Surface Reconstructionhttps://github.com/fwilliams/deep-geometric-prior





ThursdayPoster 3.1151Francis WilliamsFrancis Williams, Teseo Schneider, Claudio Silva, Denis Zorin, Joan Bruna, Daniele Panozzo

240Kervolutional Neural Networkshttps://github.com/gan3sh500/kervolution-pytorch


TuesdayOral 1.1A9:18TuesdayPoster 1.14Chen WangChen Wang, Jianfei Yang, Lihua Xie, Junsong Yuan

357Graphonomy: Universal Human Parsing via Graph Transfer Learninghttps://github.com/Gaoyiminggithub/Graphonomy





WednesdayPoster 2.272Ke GongKe Gong, Yiming Gao, Xiaodan Liang, Xiaohui Shen, Meng Wang, Liang Lin

358Pedestrian Detection With Autoregressive Network Phaseshttps://github.com/garrickbrazil/AR-Ped





WednesdayPoster 2.249Garrick BrazilGarrick Brazil, Xiaoming Liu

359Semantic Graph Convolutional Networks for 3D Human Pose Regressionhttps://github.com/garyzhao/SemGCN





TuesdayPoster 1.295Long Zhao

270Instance-Level Meta Normalizationhttps://github.com/Gasoonjia/ILM-Norm





WednesdayPoster 2.131Songhao JiaSonghao Jia, Ding-Jie Chen, Hwann-Tzong Chen

3603D Hand Shape and Pose Estimation From a Single RGB Imagehttps://github.com/geliuhao/3DHandShapePosefromRGB
https://sites.google.com/site/geliuhaontu/home/cvpr2019
ThursdayOral 3.2B13:48ThursdayPoster 3.295Liuhao GeLiuhao Ge, Zhou Ren, Yuncheng Li, Zehao Xue, Yingying Wang, Jianfei Cai, Junsong Yuan

361Generalized Intersection Over Union: A Metric and a Loss for Bounding Box Regressionhttps://github.com/generalized-iou/Detectron.pytorchhttps://mp.weixin.qq.com/s/6QsyYtEVjavoLfU_lQF1pw




TuesdayPoster 1.143Hamid RezatofighiHamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, Silvio Savarese

362Hierarchical Deep Stereo Matching on High-Resolution Imageshttps://github.com/gengshan-y/high-res-stereo
http://www.contrib.andrew.cmu.edu/~gengshay/cvpr19stereo



WednesdayPoster 2.197Gengshan YangGengshan Yang,Joshua Manela, Michael Happold,Deva Ramanan

164Generating Classification Weights With GNN Denoising Autoencoders for Few-Shot Learninghttps://github.com/gidariss/wDAE_GNN_FewShot


TuesdayOral 1.1A9:10TuesdayPoster 1.13Spyros GidarisSpyros Gidaris, Nikos Komodakis

363Learning From Synthetic Data for Crowd Counting in the Wildhttps://github.com/gjy3035/GCC-CL





WednesdayPoster 2.2166Qi WangQi Wang, Junyu Gao, Wei Lin, Yuan Yuan

364Context and Attribute Grounded Dense Captioninghttps://github.com/gjyin91/CAG-Nethttps://zhuanlan.zhihu.com/p/57822460https://gjyin91.github.io/projects/cagnet.html



WednesdayPoster 2.1201Guojun YinGuojun Yin, Lu Sheng, Bin Liu, Nenghai Yu, Xiaogang Wang, Jing Shao

13Self-Supervised GANs via Auxiliary Rotation Losshttps://github.com/google/compare_gan





ThursdayPoster 3.2138Ting ChenTing Chen, Xiaohua Zhai, Marvin Ritter, Mario Lucic, Neil Houlsby

365Neural Rerendering in the Wildhttps://github.com/google/neural_rerendering_in_the_wild


WednesdayOral 2.2C14:42WednesdayPoster 2.2142Moustafa MeshryMoustafa Meshry, Dan B Goldman, Sameh Khamis, Hugues Hoppe, Rohit Pandey, Noah Snavely, Ricardo Martin-Brualla

146Peeking Into the Future: Predicting Future Person Activities and Locations in Videoshttps://github.com/google/next-prediction





WednesdayPoster 2.1133Junwei LiangJunwei Liang, Lu Jiang, Juan Carlos Niebles, Alexander Hauptmann, Li Fei-Fei

79Revisiting Self-Supervised Visual Representation Learninghttps://github.com/google/revisiting-self-supervised





TuesdayPoster 1.1194Alexander KolesnikovAlexander Kolesnikov,?Xiaohua Zhai,?Lucas Beyer

195BubbleNets: Learning to Select the Guidance Frame in Video Object Segmentation by Deep Sorting Frameshttps://github.com/griffbr/BubbleNets


ThursdayOral 3.1C9:29ThursdayPoster 3.165Brent A. GriffinBrent A. Griffin, Jason J. Corso

366Attentive Region Embedding Network for Zero-Shot Learninghttps://github.com/gsx0/Attentive-Region-Embedding-Network-for-Zero-shot-Learning





ThursdayPoster 3.145Guo-Sen Xie

367Self-Calibrating Deep Photometric Stereo Networkshttps://github.com/guanyingc/SDPS-Net
http://gychen.org/SDPS-Net/
ThursdayOral 3.1B9:11ThursdayPoster 3.184Guanying ChenGuanying Chen, Kai Han, Boxin Shi, Yasuyuki Matsushita, Kwan-Yee K. Wong

208Object Counting and Instance Segmentation With Image-Level Supervisionhttps://github.com/GuoleiSun/CountSeg





ThursdayPoster 3.2181Hisham CholakkalHisham Cholakkal, Guolei Sun (equal contribution), Fahad Shahbaz Khan, Ling Shao

110DVC: An End-To-End Deep Video Compression Frameworkhttps://github.com/GuoLusjtu/DVC


ThursdayOral 3.2C13:40ThursdayPoster 3.2149Guo LuGuo Lu, Wanli Ouyang, Dong Xu, Xiaoyun Zhang, Chunlei Cai, Zhiyong Gao

54Toward Convolutional Blind Denoising of Real Photographshttps://github.com/GuoShi28/CBDNet





TuesdayPoster 1.1173Shi GuoShi Guo, Zifei Yan, Kai Zhang, Wangmeng Zuo, Lei Zhang

103Multi-Channel Attention Selection GAN With Cascaded Semantic Guidance for Cross-View Image Translationhttps://github.com/Ha0Tang/SelectionGAN


TuesdayOral 1.2B14:29TuesdayPoster 1.2128Hao TangHao Tang, Dan Xu, Nicu Sebe, Yanzhi Wang, Jason J. Corso, Yan Yan

987AdaptiveFace: Adaptive Margin and Sampling for Face Recognitionhttps://github.com/haoliu1994/AdaptiveFace





ThursdayPoster 3.2117Hao Liu

368Multi-Level Multimodal Common Semantic Space for Image-Phrase Groundinghttps://github.com/hassanhub/MultiGrounding





ThursdayPoster 3.2189Hassan AkbariHassan Akbari, Svebor Karaman, Surabhi Bhargava, Brian Chen, Carl Vondrick, Shih-Fu Chang

369Learning Joint Reconstruction of Hands and Manipulated Objectshttps://github.com/hassony2/manopth
https://www.di.ens.fr/willow/research/obman/



ThursdayPoster 3.285Yana HassonYana Hasson, Gül Varol, Dimitrios Tzionas, Igor Kalevatykh, Michael J. Black, Ivan Laptev, Cordelia Schmid

253The Pros and Cons: Rank-Aware Temporal Attention for Skill Determination in Long Videoshttps://github.com/hazeld/rank-aware-attention-network





WednesdayPoster 2.2114Hazel DoughtyHazel Doughty, Walterio Mayol-Cuevas, Dima Damen

370Modulating Image Restoration With Continual Levels via Adaptive Feature Modification Layershttps://github.com/hejingwenhejingwen/AdaFM


ThursdayOral 3.2C14:11ThursdayPoster 3.2154Jingwen HeJingwen He, Chao Dong, and Yu Qiao

50Mode Seeking Generative Adversarial Networks for Diverse Image Synthesishttps://github.com/HelenMao/MSGAN





TuesdayPoster 1.1144Qi MaoQi Mao, Hsin-Ying Lee, Hung-Yu Tseng, Siwei Ma, Ming-Hsuan Yang?

371Looking for the Devil in the Details: Learning Trilinear Attention Sampling Network for Fine-Grained Image Recognitionhttps://github.com/Heliang-Zheng/TASN





WednesdayPoster 2.146Heliang Zheng

159LaSOT: A High-Quality Benchmark for Large-Scale Single Object Trackinghttps://github.com/HengLan/LaSOT_Evaluation_Toolkit
https://cis.temple.edu/lasot/



WednesdayPoster 2.183Heng FanHeng Fan, Liting Lin, Fan Yang, Peng Chu, Ge Deng, Sijia Yu, Hexin Bai, Yong Xu, Chunyuan Liao, Haibin Ling

111Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationhttps://github.com/he-y/filter-pruning-geometric-median


WednesdayOral 2.1A9:11WednesdayPoster 2.18Yang HeYang He, Ping Liu, Ziwei Wang, Zhilan Hu, Yi Yang

156TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Mesheshttps://github.com/hjwdzh/TextureNet


WednesdayOral 2.1B8:40WednesdayPoster 2.1108Jingwei HuangJingwei Huang, Haotian Zhang, Li Yi, Thomas Funkhouser, Matthias Niessner, and Leonidas Guibas

36Stereo R-CNN Based 3D Object Detection for Autonomous Drivinghttps://github.com/HKUST-Aerial-Robotics/Stereo-RCNNhttps://mp.weixin.qq.com/s/X6XI7L57fGGGkAUug3E6Dg




WednesdayPoster 2.292Peiliang LiPeiliang Li, Xiaozhi Chen, Shaojie Shen

93PointNetLK: Robust & Efficient Point Cloud Registration Using PointNethttps://github.com/hmgoforth/PointNetLK





WednesdayPoster 2.224Yasuhiro AokiYasuhiro Aoki, Hunter Goforth, Rangaprasad Arun Srivatsan, Simon Lucey

373K-Nearest Neighbors Hashinghttps://github.com/HolmesShuan/K-Nearest-Neighbors-Hashing





TuesdayPoster 1.236Xiangyu HeXiangyu He and Peisong Wang and Jian Cheng

374ODE-Inspired Network Design for Single Image Super-Resolutionhttps://github.com/HolmesShuan/OISR-PyTorch





TuesdayPoster 1.1175Xiangyu HeXiangyu He and Zitao Mo and Peisong Wang and Yang Liu and Mingyuan Yang and Jian Cheng

917Deep Stacked Hierarchical Multi-Patch Network for Image Deblurringhttps://github.com/HongguangZhang/DMPHN-cvpr19-master





WednesdayPoster 2.1174Hongguang Zhang

375Neural Scene Decomposition for Multi-Person Motion Capturehttps://github.com/hrhodin/NeuralSceneDecomposition





WednesdayPoster 2.298Helge Rhodin

920FOCNet: A Fractional Optimal Control Network for Image Denoisinghttps://github.com/hsijiaxidian/FOCNet





WednesdayPoster 2.1182Xixi Jia

376PointWeb: Enhancing Local Neighborhood Features for Point Cloud Processinghttps://github.com/hszhao/PointWeb





WednesdayPoster 2.1102Hengshuang ZhaoHengshuang Zhao*, Li Jiang*, Chi-Wing Fu, and Jiaya Jia

222Iterative Normalization: Beyond Standardization Towards Efficient Whiteninghttps://github.com/huangleiBuaa/IterNorm





WednesdayPoster 2.132Lei HuangLei Huang, Yi Zhou, Fan Zhu, Li Liu, Ling Shao

98Noise-Tolerant Paradigm for Training Face Recognition CNNshttps://github.com/huangyangyu/NoiseFace





ThursdayPoster 3.2111Wei HuWei Hu, Yangyu Huang, Fan Zhang, Ruirui Li

377Deep Surface Normal Estimation With Hierarchical RGB-D Fusionhttps://github.com/huangyunmu/HFMNet_CVPR2019





WednesdayPoster 2.1192Jin Zeng

378Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationhttps://github.com/hughw19/NOCS_CVPR2019


TuesdayOral 1.2C15:00TuesdayPoster 1.2181He Wang

135Reliable and Efficient Image Cropping: A Grid Anchor Based Approachhttps://github.com/HuiZeng/Grid-Anchor-based-Image-Cropping





WednesdayPoster 2.1171Hui ZengHui Zeng, Lida Li, Zisheng Cao, Lei Zhang

244Towards Visual Feature Translationhttps://github.com/hujiecpp/VisualFeatureTranslation





TuesdayPoster 1.253Jie HuJie Hu, Rongrong Ji, Hong Liu, Shengchuan Zhang, Cheng Deng, Qi Tian

279Efficient Neural Network Compressionhttps://github.com/Hyeji-Kim/ENC





ThursdayPoster 3.2198Hyeji KimHyeji Kim, Muhammad Umar Karim Khan, Chong-Min Kyung

165Transfer Learning via Unsupervised Task Discovery for Visual Question Answeringhttps://github.com/HyeonwooNoh/vqa_task_discovery





WednesdayPoster 2.2203Hyeonwoo NohHyeonwoo Noh, Taehoon Kim, Jonghwan Mun, Bohyung Han

865CANet: Class-Agnostic Segmentation Networks With Iterative Refinement and Attentive Few-Shot Learninghttps://github.com/icoz69/CaNet





WednesdayPoster 2.167Chi Zhang

254Factor Graph Attentionhttps://github.com/idansc/fga





TuesdayPoster 1.1206Idan SchwartzIdan Schwartz, Seunghak Yu, Tamir Hazan, Alexander Schwing

263A Simple Baseline for Audio-Visual Scene-Aware Dialoghttps://github.com/idansc/simple-avsd





ThursdayPoster 3.2196Idan SchwartzIdan Schwartz, Alexander Schwing, Tamir Hazan

1294Deep Incremental Hashing Network for Efficient Image Retrievalhttps://github.com/IIE-MR/DIHN





ThursdayPoster 3.112Dayan Wu

85RVOS: End-To-End Recurrent Network for Video Object Segmentationhttps://github.com/imatge-upc/rvos





WednesdayPoster 2.173Carles VenturaCarles Ventura, Miriam Bellver, Andreu Girbau, Amaia Salvador, Ferran Marques, Xavier Giro-i-Nieto

25Selective Kernel Networkshttps://github.com/implus/SKNet





TuesdayPoster 1.128Xiang LiXiang Li, Wenhai Wang, Xiaolin Hu, Jian Yang

264SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration Without Correspondenceshttps://github.com/intellhave/SDRSAC


TuesdayOral 1.1B9:00TuesdayPoster 1.172Huu M. LeHuu Le, Thanh-Toan Do, Tuan Hoang, Ngai-Man Cheung

594Structured Knowledge Distillation for Semantic Segmentationhttps://github.com/irfanICMLL/structure_knowledge_distillationhttps://mp.weixin.qq.com/s/WvYPf7xHu4TtuDan_Hh_pQ

TuesdayOral 1.2C14:34TuesdayPoster 1.2177Yifan LiuYifan Liu, Ke Chen, Chris Liu, Zengchang Qin, Zhenbo Luo, Jingdong Wang

235HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNshttps://github.com/irvinxav/Efficient-HetConv-Heterogeneous-Kernel-Based-Convolutions





WednesdayPoster 2.128Pravendra SinghPravendra Singh, Vinay Kumar Verma, Piyush Rai, Vinay P. Namboodiri

379RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completionhttps://github.com/iSarmad/RL-GAN-Net





WednesdayPoster 2.1166Muhammad SarmadMuhammad Sarmad, Hyunjoo Jenny Lee, Young Min Kim

380ManTra-Net: Manipulation Tracing Network for Detection and Localization of Image Forgeries With Anomalous Featureshttps://github.com/ISICV/ManTraNet





ThursdayPoster 3.176Yue Wu

271AIRD: Adversarial Learning Framework for Image Repurposing Detectionhttps://github.com/isi-vista/AIRD-Datasets





ThursdayPoster 3.236Ayush JaiswalAyush Jaiswal, Yue Wu, Wael AbdAlmageed, Iacopo Masi, Premkumar Natarajan

31DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusionhttps://github.com/j96w/DenseFusionhttps://mp.weixin.qq.com/s/wrND2cocWlPPVXPqpq-Glg




TuesdayPoster 1.287Chen WangChen Wang, Danfei Xu, Yuke Zhu, Roberto Martín-Martín, Cewu Lu, Li Fei-Fei, Silvio Savarese

295DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentationhttps://github.com/j-a-lin/DFANet_PyTorch





ThursdayPoster 3.174Hanchao LiHanchao Li, Pengfei Xiong, Haoqiang Fan, Jian Sun

381Adversarial Inference for Multi-Sentence Video Descriptionhttps://github.com/jamespark3922/adv-inf


WednesdayOral 2.2B13:40WednesdayPoster 2.2179Jae Sung ParkJae Sung Park,?Marcus Rohrbach,?Trevor Darrell,?Anna Rohrbach

201Locating Objects Without Bounding Boxeshttps://github.com/javiribera/locating-objects-without-bboxes


WednesdayOral 2.2A14:16WednesdayPoster 2.233Javier RiberaJavier Ribera, David Güera, Yuhao Chen, Edward J. Delp

173Destruction and Construction Learning for Fine-Grained Image Recognitionhttps://github.com/JDAI-CV/DCL





WednesdayPoster 2.161Yue Chen

83CrowdPose: Efficient Crowded Scenes Pose Estimation and a New Benchmarkhttps://github.com/Jeff-sjtu/CrowdPose


ThursdayOral 3.2B14:06ThursdayPoster 3.298Jiefeng LiJiefeng Li, Can Wang, Hao Zhu, Yihuan Mao, Hao-Shu Fang, Cewu Lu

121Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defenseshttps://github.com/jeromerony/fast_adversarial


WednesdayOral 2.1A8:58WednesdayPoster 2.16Jerome RonyJér?me Rony, Luiz G. Hafemann, Luiz S. Oliveira, Ismail Ben Ayed, Robert Sabourin, Eric Granger

196REPAIR: Removing Representation Bias by Dataset Resamplinghttps://github.com/JerryYLi/Dataset-REPAIR





ThursdayPoster 3.194Yi LiYi Li, Nuno Vasconcelos

147Attention-Aware Multi-Stroke Style Transferhttps://github.com/JianqiangRen/AAMS
https://sites.google.com/view/yuanyao/attention-aware-multi-stroke-style-transfer



TuesdayPoster 1.1148Yuan YaoYuan Yao, Jianqiang Ren, Xuansong Xie, Weidong Liu, Yong-Jin Liu, Jun Wang

245Dance With Flow: Two-In-One Stream Action Detectionhttps://github.com/jiaozizhao/Two-in-One-ActionDetection





ThursdayPoster 3.1131Jiaojiao ZhaoJiaojiao Zhao, Cees G.M. Snoek

382ComDefend: An Efficient Image Compression Model to Defend Adversarial Exampleshttps://github.com/jiaxiaojunQAQ/Comdefendhttps://zhuanlan.zhihu.com/p/62232536




WednesdayPoster 2.1185Xiaojun JiaXiaojun Jia, Xingxing Wei, Xiaochun Cao, Hassan Foroosh

696Attention-Guided Network for Ghost-Free High Dynamic Range Imaginghttps://github.com/JimmyChame/The-State-of-the-Art-in-HDR-Deghosting





TuesdayPoster 1.1177Qingsen Yan

383Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relationshttps://github.com/jiwoon-ahn/irn


TuesdayOral 1.2A14:11TuesdayPoster 1.225Jiwoon AhnJiwoon Ahn, Sunghyun Cho, Suha Kwak

1086CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depthhttps://github.com/jmfacil/camconvs
http://webdiis.unizar.es/~jmfacil/camconvs/



ThursdayPoster 3.287Jose M. FacilJose M. Facil, Benjamin Ummenhofer, Huizhong Zhou, Luis Montesano, Thomas Brox, Javier Civera

246A Generative Appearance Model for End-To-End Video Object Segmentationhttps://github.com/joakimjohnander/agame-vos


ThursdayOral 3.1C9:52ThursdayPoster 3.169Joakim JohnanderJoakim Johnander, Martin Danelljan, Emil Brissman, Fahad Shahbaz Khan, Michael Felsberg

384Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilizationhttps://github.com/joe-siyuan-qiao/NeuralRejuvenation-CVPR19


TuesdayOral 1.1A9:36TuesdayPoster 1.17Siyuan QiaoSiyuan Qiao, Zhe Lin, Jianming Zhang, Alan Yuille

385FastDraw: Addressing the Long Tail of Lane Detection by Adapting a Sequential Prediction Networkhttps://github.com/jonahthelion/FastDraw





ThursdayPoster 3.262Jonah PhilionJonah Philion

386A General and Adaptive Robust Loss Functionhttps://github.com/jonbarron/robust_loss_pytorch


WednesdayOral 2.1A9:06WednesdayPoster 2.17Jonathan T. BarronJonathan T. Barron

387A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervisionhttps://github.com/JosephineRabbit/MLMSNet





WednesdayPoster 2.2161Runmin WuRunmin Wu, Mengyang Feng, Wenlong Guan, Dong Wang, Huchuan Lu, Errui Ding

217Scale-Adaptive Neural Dense Features: Learning via Hierarchical Context Aggregationhttps://github.com/jspenmar/SAND_features





WednesdayPoster 2.1197Jaime SpencerJaime Spencer, Richard Bowden, Simon Hadfield

166Noise2Void - Learning Denoising From Single Noisy Imageshttps://github.com/juglab/n2v





TuesdayPoster 1.1215Alexander KrullAlexander Krull, Tim-Oliver Buchholz, Florian Jug

247Unsupervised Open Domain Recognition by Semantic Discrepancy Minimizationhttps://github.com/junbaoZHUO/UODTN





TuesdayPoster 1.152Junbao ZhuoJunbao Zhuo, Shuhui Wang, Shuhao Cui, Qingming Huang

16Dual Attention Network for Scene Segmentationhttps://github.com/junfu1115/DANet





TuesdayPoster 1.267Jun FuJun Fu, Jing Liu, Haijie Tian, Yong Li, Yongjun Bao, Zhiwei Fang, Hanqing Lu

90FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchhttps://github.com/JunrQ/NAS


ThursdayOral 3.2A14:34ThursdayPoster 3.212Bichen WuBichen Wu, Xiaoliang Dai, Peizhao Zhang, Yanghan Wang, Fei Sun, Yiming Wu, Yuandong Tian, Peter Vajda, Yangqing Jia, Kurt Keutzer

388Attention-Based Dropout Layer for Weakly Supervised Object Localizationhttps://github.com/junsukchoe/ADL


TuesdayOral 1.2A14:16TuesdayPoster 1.226Junsuk Choe

108Video Generation From Single Semantic Label Maphttps://github.com/junting/seg2vid





TuesdayPoster 1.2144Junting PanJunting Pan, Chengyu Wang, Xu Jia, Jing Shao, Lu Sheng, Junjie Yan, Xiaogang Wang

389Natural and Realistic Single Image Super-Resolution With Explicit Natural Manifold Discriminationhttps://github.com/JWSoh/NatSR





WednesdayPoster 2.2158Jae Woong Soh

390Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detectionhttps://github.com/JXingZhao/ContrastPrior





TuesdayPoster 1.2164Jia-Xing ZhaoZhao, Jia-Xing and Cao, Yang and Fan, Deng-Ping and Cheng, Ming-Ming and Li, Xuan-Yi and Zhang, Le

391Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detectionhttps://github.com/jx-zhong-for-academic-purpose/GCN-Anomaly-Detection





TuesdayPoster 1.1125Jia-Xing Zhong

392Learning to Compose Dynamic Tree Structures for Visual Contextshttps://github.com/KaihuaTang/VCTree-Visual-Question-Answering


WednesdayOral 2.2B13:53WednesdayPoster 2.2181Kaihua TangKaihua Tang, Hanwang Zhang, Baoyuan Wu, Wenhan Luo, Wei Liu

393A Kernelized Manifold Mapping to Diminish the Effect of Adversarial Perturbationshttps://github.com/kakumarabhishek/KernelizedManifoldMapping-1





ThursdayPoster 3.237Saeid Asgari TaghanakiSaeid Asgari Taghanaki, Kumar Abhishek, Shekoofeh Azizi, Ghassan Hamarneh

296QATM: Quality-Aware Template Matching for Deep Learninghttps://github.com/kamata1729/QATM_pytorch





ThursdayPoster 3.259Jiaxin ChengJiaxin Cheng, Yue Wu, Wael Abd-Almageed, Premkumar Natarajan

284Complete the Look: Scene-Based Complementary Product Recommendationhttps://github.com/kang205/STL-Dataset





ThursdayPoster 3.1207Wang-Cheng KangWang-Cheng Kang, Eric Kim, Jure Leskovec, Charles Rosenberg, Julian McAuley

394Semantic Projection Network for Zero- and Few-Label Semantic Segmentationhttps://github.com/kazuto1011/deeplab-pytorch





WednesdayPoster 2.2172Yongqin Xian

180Tactical Rewind: Self-Correction via Backtracking in Vision-And-Language Navigationhttps://github.com/Kelym/FAST


WednesdayOral 2.2B15:05WednesdayPoster 2.2193Liyiming KeLiyiming Ke, Xiujun Li, Yonatan Bisk, Ari Holtzman, Zhe Gan, Jingjing Liu, Jianfeng Gao, Yejin Choi, Siddhartha Srinivasa

236Edge-Labeling Graph Neural Network for Few-Shot Learninghttps://github.com/khy0809/fewshot-egnn


TuesdayOral 1.1A9:05TuesdayPoster 1.12Jongmin KimJongmin Kim, Taesup Kim, Sungwoong Kim, Chang D. Yoo

63ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratchhttps://github.com/KimSoybean/ScratchDethttps://mp.weixin.qq.com/s/TZj0QzDXE6QbCY5-pT6RNQ

TuesdayOral 1.2A14:47TuesdayPoster 1.231Rui ZhuRui Zhu, Shifeng Zhang, Xiaobo Wang, Longyin Wen, Hailin Shi, Liefeng Bo, Tao Mei?

75Meta-Learning With Differentiable Convex Optimizationhttps://github.com/kjunelee/MetaOptNet


ThursdayOral 3.2A13:48ThursdayPoster 3.24Kwonjoon LeeKwonjoon Lee, Subhransu Maji, Avinash Ravichandran, Stefano Soatto

112FineGAN: Unsupervised Hierarchical Disentanglement for Fine-Grained Object Generation and Discoveryhttps://github.com/kkanshul/finegan


WednesdayOral 2.2A14:24WednesdayPoster 2.234Krishna Kumar SinghKrishna Kumar Singh, Utkarsh Ojha, Yong Jae Lee

70Unsupervised Person Re-Identification by Soft Multilabel Learninghttps://github.com/KovenYu/MAR


TuesdayOral 1.2A13:35TuesdayPoster 1.219Hong-Xing YuHong-Xing Yu, Wei-Shi Zheng, Ancong Wu, Xiaowei Guo, Shaogang Gong, Jian-Huang Lai?

272Representation Similarity Analysis for Efficient Task Taxonomy & Transfer Learninghttps://github.com/kshitijd20/RSA-CVPR19-release





ThursdayPoster 3.2180Kshitij DwivediKshitij Dwivedi, Gemma Roig

395DeepCO3: Deep Instance Co-Segmentation by Co-Peak Search and Co-Saliency Detectionhttps://github.com/KuangJuiHsu/DeepCO3?


ThursdayOral 3.1C8:48ThursdayPoster 3.158Kuang-Jui HsuKuang-Jui Hsu, Yen-Yu Lin, Yung-Yu Chuang

396Deep Metric Learning to Rankhttps://github.com/kunhe/FastAP-metric-learning





TuesdayPoster 1.1188Fatih CakirFatih Cakir*,?Kun He*,?Xide Xia,?Brian Kulis, and?Stan Sclaroff

297Additive Adversarial Learning for Unbiased Authenticationhttps://github.com/langlrsw/AAL-unbiased-authentication





ThursdayPoster 3.246Jian LiangJian Liang, Yuren Cao, Chenbin Zhang, Shiyu Chang, Kun Bai, Zenglin Xu

1098HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-Scale Point Cloudshttps://github.com/laoreja/HPLFlowNet





TuesdayPoster 1.278Xiuye Gu

248Learning Cross-Modal Embeddings With Adversarial Networks for Cooking Recipes and Food Imageshttps://github.com/LARC-CMU-SMU/ACME





ThursdayPoster 3.261Hao WangHao Wang, Doyen Sahoo, Chenghao Liu, Ee-peng Lim, Steven C. H. Hoi?

8203DN: 3D Deformation Networkhttps://github.com/laughtervv/3DN





TuesdayPoster 1.193Weiyue Wang

223Self-Supervised Spatio-Temporal Representation Learning for Videos by Predicting Motion and Appearance Statisticshttps://github.com/laura-wang/video_repres_mas





TuesdayPoster 1.2190Jiangliu WangJiangliu Wang, Jianbo Jiao, Linchao Bao, Shengfeng He, Yunhui Liu, Wei Liu

846Explore-Exploit Graph Traversal for Image Retrievalhttps://github.com/layer6ai-labs/egt





ThursdayPoster 3.149Cheng Chang

11Joint Discriminative and Generative Learning for Person Re-Identificationhttps://github.com/layumi/Person_reID_baseline_pytorchhttps://mp.weixin.qq.com/s/51X7NIS1UEXJ1sqx54tuwg

TuesdayOral 1.2A13:30TuesdayPoster 1.218Zhedong ZhengZhedong Zheng, Xiaodong Yang, Zhiding Yu, Liang Zheng, Yi Yang, Jan Kautz

298Isospectralization, or How to Hear Shape, Style, and Correspondencehttps://github.com/lcosmo/isospectralization





WednesdayPoster 2.280Luca CosmoLuca Cosmo, Mikhail Panine, Arianna Rampini, Maks Ovsjanikov, Michael M. Bronstein, Emanuele Rodolà

397Hierarchical Cross-Modal Talking Face Generation With Dynamic Pixel-Wise Losshttps://github.com/lelechen63/ATVGnet





WednesdayPoster 2.2111Lele ChenLele Chen , Ross K Maddox, Zhiyao Duan, Chenliang Xu

398Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondencehttps://github.com/lelimite4444/BridgeDepthFlow





TuesdayPoster 1.1191Hsueh-Ying LaiHsueh-Ying Lai, Yi-Hsuan Tsai, Wei-Chen Chiu

504LaSO: Label-Set Operations Networks for Multi-Label Few-Shot Learninghttps://github.com/leokarlin/LaSO


WednesdayOral 2.2A15:00WednesdayPoster 2.240Amit Alfassy

127Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on N-Sphereshttps://github.com/leoshine/Spherical_Regression





ThursdayPoster 3.1113Shuai LiaoShuai Liao, Efstratios Gavves, Cees G. M. Snoek

10Deep High-Resolution Representation Learning for Human Pose Estimationhttps://github.com/leoxiaobin/deep-high-resolution-net.pytorchhttps://mp.weixin.qq.com/s/ZRCzBTBmlEzQCVo1HLWtbQ




WednesdayPoster 2.1130Ke SunKe Sun, Bin Xiao, Dong Liu, Jingdong Wang

399Multi-Target Embodied Question Answeringhttps://github.com/lichengunc/mteqa





WednesdayPoster 2.1208Licheng YuYu, Licheng and Chen, Xinlei and Gkioxari, Georgia and Bansal, Mohit and Berg, Tamara L and Batra, Dhruv

202Leveraging the Invariant Side of Generative Zero-Shot Learninghttps://github.com/lijin118/LisGAN





WednesdayPoster 2.267Jingjing LiJingjing Li, Mengmeng Jin, Ke Lu, Zhengming Ding, Lei Zhu, Zi Huang

400Learning to Learn From Noisy Labeled Datahttps://github.com/LiJunnan1992/MLNT





WednesdayPoster 2.150Junnan LiJunnan Li, Y. Wong, Qi Zhao, M. Kankanhalli

187Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognitionhttps://github.com/limaosen0/AS-GCN





TuesdayPoster 1.2112Maosen LiMaosen Li, Siheng Chen, Xu Chen, Ya Zhang, Yanfeng Wang, and Qi Tian

53Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregationhttps://github.com/LinZhuoChen/DUpsampling





TuesdayPoster 1.265Zhi TianZhi Tian, Chunhua Shen, Tong He, Youliang Yanl

197Label Efficient Semi-Supervised Learning via Graph Filteringhttps://github.com/liqimai/Efficient-SSL





ThursdayPoster 3.195Qimai LiQimai Li,Xiao-Ming Wu,Han Liu,Xiaotong Zhang

87Pose2Seg: Detection Free Human Instance Segmentationhttps://github.com/liruilong940607/Pose2Seg
http://www.liruilong.cn/Pose2Seg/index.html?



TuesdayPoster 1.166Song-Hai ZhangSong-Hai Zhang, Ruilong Li, Xin Dong, Paul L. Rosin, Zixi Cai, Han Xi, Dingcheng Yang, Hao-Zhi Huang, Shi-Min Hu

181Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learninghttps://github.com/liruoteng/HeavyRainRemoval





TuesdayPoster 1.1165Ruoteng LiRuotent Li, Loong Fah Cheong, Robby T. Tan

211Lending Orientation to Neural Networks for Cross-View Geo-Localizationhttps://github.com/Liumouliu/OriCNN





WednesdayPoster 2.1123Liu LiuLiu Liu, Hongdong Li

218Dual Residual Networks Leveraging the Potential of Paired Operations for Image Restorationhttps://github.com/liu-vis/DualResidualNetworks





WednesdayPoster 2.28Xing LiuXing Liu, Masanori Suganuma, Zhun Sun, Takayuki Okatani

34High-Level Semantic Feature Detection: A New Perspective for Pedestrian Detectionhttps://github.com/liuwei16/CSP





WednesdayPoster 2.164Wei LiuZhao-Min Chen, Xiu-Shen Wei Peng Wang3Yanwen Guo

106Partial Order Pruning: For Best Speed/Accuracy Trade-Off in Neural Architecture Searchhttps://github.com/lixincn2015/Partial-Order-Pruning





ThursdayPoster 3.120Xin LiXin Li, Yiming Zhou, Zheng Pan, Jiashi Feng

128Bidirectional Learning for Domain Adaptation of Semantic Segmentationhttps://github.com/liyunsheng13/BDL
https://voca.is.tue.mpg.de/



WednesdayPoster 2.21Yunsheng LiYunsheng Li, Lu Yuan, Nuno Vasconcelos

57Occupancy Networks: Learning 3D Reconstruction in Function Spacehttps://github.com/LMescheder/Occupancy-Networks


WednesdayOral 2.1B8:53WednesdayPoster 2.1110Lars MeschederLars Mescheder and Michael Oechsle and Michael Niemeyer and Sebastian Nowozin and Andreas Geiger

401Learning Parallax Attention for Stereo Image Super-Resolutionhttps://github.com/LongguangWang/PASSRnet





ThursdayPoster 3.2166Longguang WangLongguang Wang, Yingqian Wang, Zhengfa Liang, Zaiping Lin, Jungang Yang, Wei An, Yulan Guo

120Spatiotemporal CNN for Video Object Segmentationhttps://github.com/longyin880815/STCNN





TuesdayPoster 1.1139Kai XuKai Xu, Longyin Wen, Guorong Li, Liefeng Bo, Qingming Huang

109End-To-End Multi-Task Learning With Attentionhttps://github.com/lorenmt/mtan





TuesdayPoster 1.1189Shikun LiuShikun Liu, Edward Johns, Andrew J. Davison

285MAP Inference via Block-Coordinate Frank-Wolfe Algorithmhttps://github.com/LPMP/LPMP


ThursdayOral 3.2C15:05ThursdayPoster 3.2163Paul SwobodaPaul Swoboda, Vladimir Kolmogorov

402Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognitionhttps://github.com/lshiwjx/2s-AGCN





ThursdayPoster 3.2125Lei Shi

152Single Image Deraining: A Comprehensive Benchmark Analysishttps://github.com/lsy17096535/Single-Image-Deraining





TuesdayPoster 1.2155Siyuan LiSiyuan Li, Iago Breno Araujo, Wenqi Ren, Zhangyang Wang, Eric K. Tokuda, Roberto Hirata Junior, Roberto Cesar-Junior, Jiawan Zhang, Xiaojie Guo, Xiaochun Cao

188SparseFool: A Few Pixels Make a Big Differencehttps://github.com/LTS4/SparseFool





ThursdayPoster 3.114Apostolos ModasApostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard

155Taking a Deeper Look at the Inverse Compositional Algorithmhttps://github.com/lvzhaoyang/DeeperInverseCompositionalAlgorithm


WednesdayOral 2.1C8:35WednesdayPoster 2.1136Zhaoyang LvZhaoyang Lv, Frank Dellaert, James M. Rehg, Andreas Geiger

403Dense Intrinsic Appearance Flow for Human Pose Transferhttps://github.com/ly015/intrinsic_flow?





TuesdayPoster 1.2140Yining LiYining Li, Chen Huang, Chen Change Loy

60Pluralistic Image Completionhttps://github.com/lyndonzheng/Pluralistic-Inpainting
http://www.chuanxiaz.com/publication/pluralistic/



TuesdayPoster 1.1145Chuanxia ZhengChuanxia Zheng, Tat-Jen Cham, Jianfei Cai?

404TopNet: Structural Point Cloud Decoderhttps://github.com/lynetcha/completion3d





TuesdayPoster 1.115Lyne P. TchapmiTchapmi, Lyne P and Kosaraju, Vineet and Rezatofighi, S. Hamid and Reid, Ian and Savarese, Silvio

113Attention Branch Network: Learning of Attention Mechanism for Visual Explanationhttps://github.com/machine-perception-robotics-group/attention_branch_network


ThursdayOral 3.2A14:16ThursdayPoster 3.29Hiroshi FukuiHiroshi Fukui, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi

405End-To-End Efficient Representation Learning via Cascading Combinatorial Optimizationhttps://github.com/maestrojeong/Deep-Hash-Table-CVPR19?





ThursdayPoster 3.241Yeonwoo JeongYeonwoo Jeong, Yoonsuing Kim, Hyun Oh Song

406Multi-Similarity Loss With General Pair Weighting for Deep Metric Learninghttps://github.com/MalongTech/research-ms-loss?





WednesdayPoster 2.147Xun WangXun Wang, Xintong Han, Weilin Huang, Dengke Dong, Matthew R. Scott

189Unsupervised Embedding Learning via Invariant and Spreading Instance Featurehttps://github.com/mangye16/Unsupervised_Embedding_Learning





WednesdayPoster 2.1198Mang YeMang Ye, Xu Zhang, Pong C. Yuen, Shih-Fu Chang

407Seamless Scene Segmentationhttps://github.com/mapillary/seamseg





WednesdayPoster 2.2174Lorenzo PorziLorenzo Porzi, Samuel Rota Bulò, Aleksander Colovic, Peter Kontschieder

198AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations Rather Than Datahttps://github.com/maple-research-lab/AET


TuesdayOral 1.2C13:58TuesdayPoster 1.2171Liheng ZhangLiheng Zhang, Guo-Jun Qi, Liqiang Wang, Jiebo Luo

408Light Field Messaging With Deep Photographic Steganographyhttps://github.com/mathski/LFM





TuesdayPoster 1.1153Eric WengrowskiEric Wengrowski and Kristin Dana

280Robustness of 3D Deep Learning in an Adversarial Settinghttps://github.com/matthewwicker/IterativeSalienceOcclusion





ThursdayPoster 3.281Matthew WickerMatthew Wicker, Marta Kwiatkowska

409Guided Stereo Matchinghttps://github.com/mattpoggi/guided-stereo





TuesdayPoster 1.187Matteo PoggiMatteo Poggi, Davide Pallotti, Fabio Tosi and Stefano Mattoccia,

237A Cross-Season Correspondence Dataset for Robust Semantic Segmentationhttps://github.com/maunzzz/cross-season-segmentation





ThursdayPoster 3.175Mans LarssonM?ns Larsson, Erik Stenborg, Lars Hammarstrand, Torsten Sattler, Mark Pollefeys, Fredrik Kahl

410Why ReLU Networks Yield High-Confidence Predictions Far Away From the Training Data and How to Mitigate the Problemhttps://github.com/max-andr/relu_networks_overconfident


TuesdayOral 1.1A9:23TuesdayPoster 1.15Matthias HeinMatthias Hein, Maksym Andriushchenko, Julian Bitterwolf

897Rethinking the Evaluation of Video Summarieshttps://github.com/mayu-ot/rethinking-evs





WednesdayPoster 2.287Mayu Otani

411Deep Blind Video Decaptioning by Temporal Aggregation and Recurrencehttps://github.com/mcahny/Deep_Blind_Video_Decaptioning?





TuesdayPoster 1.2216Dahun KimDahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon

412Deep Video Inpaintinghttps://github.com/mcahny/Deep_Video_Inpainting





WednesdayPoster 2.1155Dahun KimDahun Kim, Sanghyun Woo, Joon-Young Lee, In So Kweon

413Learning to Extract Flawless Slow Motion From Blurry Videoshttps://github.com/MeiguangJin/slow-motion





WednesdayPoster 2.2157Meiguang JinJin, Meiguang and Hu, Zhe and Favaro, Paolo

157SIXray: A Large-Scale Security Inspection X-Ray Benchmark for Prohibited Item Discovery in Overlapping Imageshttps://github.com/MeioJane/SIXray





TuesdayPoster 1.1214Caijing MiaoCaijing Miao, Lingxi Xie, Fang Wan, Chi Su, Hongye Liu, Jianbin Jiao, Qixiang Ye

414Self-Supervised 3D Hand Pose Estimation Through Training by Fittinghttps://github.com/melonwan/sphereHand


ThursdayOral 3.2B13:58ThursdayPoster 3.297Chengde Wan

38Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationhttps://github.com/MenghaoGuo/AutoDeeplab


TuesdayOral 1.1A9:46TuesdayPoster 1.19Chenxi LiuPeng Zhang, Fuhao Zou, Zhiwen Wu, Nengli Dai, Skarpness Mark, Michael Fu, Juan Zhao, Kai Li

273SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perceptionhttps://github.com/mengyuest/SIGNet
https://mengyuest.github.io/SIGNet/



ThursdayPoster 3.1118Yue MengY. Meng, Y. Lu, A. Raj, S. Sunarjo, R. Guo, T. Javidi, G. Bansal, D. Bharadia

249Variational Prototyping-Encoder: One-Shot Learning With Prototypical Imageshttps://github.com/mibastro/VPE





ThursdayPoster 3.153Junsik KimJunsik Kim, Tae-Hyun Oh, Seokju Lee, Fei Pan, In So Kweon

78D2-Net: A Trainable CNN for Joint Description and Detection of Local Featureshttps://github.com/mihaidusmanu/d2-net
https://dsmn.ml/publications/d2-net.html



WednesdayPoster 2.2155Mihai DusmanuMihai Dusmanu,?Ignacio Rocco,?Tomas Pajdla,?Marc Pollefeys,?Josef Sivic,?Akihiko Torii,?Torsten Sattler

49Pseudo-LiDAR From Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Drivinghttps://github.com/mileyan/pseudo_lidar
https://mileyan.github.io/pseudo_lidar/



WednesdayPoster 2.2209Yan WangYan Wang, Wei-Lun Chao, Divyansh Garg, Bharath Hariharan, Mark Campbell, Kilian Q. Weinberger

415Deep Modular Co-Attention Networks for Visual Question Answeringhttps://github.com/MILVLG/mcan-vqa





WednesdayPoster 2.1205Zhou YuZhou Yu, Jun Yu, Yuhao Cui, Dacheng Tao, Qi Tian

20HAQ: Hardware-Aware Automated Quantization With Mixed Precisionhttps://github.com/MIT-HAN-LAB/ProxylessNAS
https://hanlab.mit.edu/projects/haq/
ThursdayOral 3.1A9:24ThursdayPoster 3.1199Kuan WangKuan Wang,?Zhijian Liu,?Yujun Lin,?Ji Lin,?Song Han

41Self-Supervised Learning of 3D Human Pose Using Multi-View Geometryhttps://github.com/mkocabas/EpipolarPose





TuesdayPoster 1.197Muhammed KocabasMuhammed Kocabas, Salih Karagoz, Emre Akbas

89PoseFix: Model-Agnostic General Human Pose Refinement Networkhttps://github.com/mks0601/PoseFix_RELEASE





WednesdayPoster 2.2105Gyeongsik MoonGyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee

286Meta-Learning Convolutional Neural Architectures for Multi-Target Concrete Defect Classification With the COncrete DEfect BRidge IMage Datasethttps://github.com/MrtnMndt/meta-learning-CODEBRIM





ThursdayPoster 3.222Martin MundtMartin Mundt, Sagnik Majumder, Sreenivas Murali, Panagiotis Panetsos, Visvanathan Ramesh

5Deformable ConvNets V2: More Deformable, Better Resultshttps://github.com/msracver/Deformable-ConvNets





ThursdayPoster 3.137Xizhou ZhuXizhou Zhu,?Han Hu,?Stephen Lin,?Jifeng Dai

212Query-Guided End-To-End Person Searchhttps://github.com/munjalbharti/Query-guided-End-to-End-Person-Search





TuesdayPoster 1.158Bharti MunjalBharti Munjal, Sikandar Amin, Federico Tombari, Fabio Galasso

203Sliced Wasserstein Generative Modelshttps://github.com/musikisomorphie/swd





TuesdayPoster 1.2142Jiqing WuJiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc Van Gool

416Unsupervised Face Normalization With Extreme Pose and Expression in the Wildhttps://github.com/mx54039q/fnm





ThursdayPoster 3.1122Yichen QianQian, Yichen and Deng, Weihong and Hu, Jiani

500Self-Supervised Representation Learning From Videos for Facial Action Unit Detectionhttps://github.com/mysee1989/TCAE


ThursdayOral 3.2B14:42ThursdayPoster 3.2104Yong Li

921RegularFace: Deep Face Recognition via Exclusive Regularizationhttps://github.com/naimple/regular-face-cvpr2019





TuesdayPoster 1.1103Kai Zhao

502SiCloPe: Silhouette-Based Clothed Peoplehttps://github.com/nanopoteto/SiCloPe_CVPR


WednesdayOral 2.1B9:06WednesdayPoster 2.1112Ryota Natsume

287Out-Of-Distribution Detection for Generalized Zero-Shot Action Recognitionhttps://github.com/naraysa/gzsl-od





ThursdayPoster 3.1136Devraj MandalDevraj Mandal, Sanath Narayan, Saikumar Dwivedi, Vikram Gupta, Shuaib Ahmed, Fahad Shahbaz Khan, Ling Shao

219BASNet: Boundary-Aware Salient Object Detectionhttps://github.com/NathanUA/BASNet





WednesdayPoster 2.275Xuebin QinZichen Zhang, Chenyang Huang, Chao Gao, Masood Dehghan and Martin Jagersand

160Camera Lens Super-Resolutionhttps://github.com/ngchc/CameraSR





TuesdayPoster 1.1167Chang ChenChang Chen, Zhiwei Xiong, Xinmei Tian, Zheng-Jun Zha, Feng Wu

74Style Transfer by Relaxed Optimal Transport and Self-Similarityhttps://github.com/nkolkin13/STROTSS





ThursdayPoster 3.1143Nicholas KolkinNicholas Kolkin, Jason Salavon, Gregory Shakhnarovich

417Convolutional Mesh Regression for Single-Image Human Shape Reconstructionhttps://github.com/nkolot/GraphCMR


WednesdayOral 2.1B9:16WednesdayPoster 2.1114Nikos KolotourosNikos Kolotouros, Georgios Pavlakos, Kostas Daniilidis

213Timeception for Complex Action Recognitionhttps://github.com/noureldien/timeception


TuesdayOral 1.1C9:05TuesdayPoster 1.1110Noureldien HusseinNoureldien Hussein, Efstratios Gavves, Arnold W.M. Smeulders

914OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representationshttps://github.com/nuclearboy95/Anomaly-Detection-OCGAN-tensorflowhttps://mp.weixin.qq.com/s/FXKWP4OlUsprSDgU7ue8CA?




TuesdayPoster 1.242Pramuditha PereraPramuditha Perera, Ramesh Nallapati, Bing Xiang

46PointPillars: Fast Encoders for Object Detection From Point Cloudshttps://github.com/nutonomy/second.pytorch





ThursdayPoster 3.2211Alex H. LangAlex H. Lang, Sourabh Vora, Holger Caesar, Lubing Zhou, Jiong Yang, Oscar Beijbom

418Improving Semantic Segmentation via Video Propagation and Label Relaxationhttps://github.com/NVIDIA/semantic-segmentation


ThursdayOral 3.1C8:53ThursdayPoster 3.159Yi ZhuYi Zhu, Karan Sapra, Fitsum A. Reda, Kevin J. Shih, Shawn Newsam, Andrew Tao, Bryan Catanzaro

419Pixel-Adaptive Convolutional Neural Networkshttps://github.com/NVlabs/pacnet





ThursdayPoster 3.219Hang SuHang Su, Varun Jampani, Deqing Sun, Orazio Gallo, Erik Learned-Miller, and Jan Kautz.

40PlaneRCNN: 3D Plane Detection and Reconstruction From a Single Imagehttps://github.com/NVlabs/planercnn
https://research.nvidia.com/publication/2019-06_PlaneRCNN
WednesdayOral 2.1B8:48WednesdayPoster 2.1109Chen LiuChen Liu, Kihwan Kim, Jinwei Gu, Yasutaka Furukawa, Jan Kautz

420SCOPS: Self-Supervised Co-Part Segmentationhttps://github.com/NVlabs/SCOPS
https://varunjampani.github.io/scops/



TuesdayPoster 1.164Wei-Chih HungWei-Chih Hung        Varun Jampani        Sifei Liu        Pavlo Molchanov        Ming-Hsuan Yang        Jan Kautz

3Semantic Image Synthesis With Spatially-Adaptive Normalizationhttps://github.com/NVlabs/SPADE


TuesdayOral 1.2B13:40TuesdayPoster 1.2120Taesung ParkTaesung Park, Ming-Yu Liu, Ting-Chun Wang, Jun-Yan Zhu

2A Style-Based Generator Architecture for Generative Adversarial Networkshttps://github.com/NVlabs/stylegan

GANWednesdayOral 2.1A9:47WednesdayPoster 2.114Tero KarrasTero Karras (NVIDIA), Samuli Laine (NVIDIA), Timo Aila (NVIDIA)

421Importance Estimation for Neural Network Pruninghttps://github.com/NVlabs/Taylor_pruning





ThursdayPoster 3.229Pavlo MolchanovPavlo Molchanov, Arun Mallya, Stephen Tyree, Iuri Frosio, Jan Kautz

422Devil Is in the Edges: Learning Semantic Boundaries From Noisy Annotationshttps://github.com/nv-tlabs/STEAL
https://nv-tlabs.github.io/STEAL/?
ThursdayOral 3.2C14:24ThursdayPoster 3.2156David AcunaDavid Acuna, Amlan Kar, Sanja Fidler

423Libra R-CNN: Towards Balanced Learning for Object Detectionhttps://github.com/OceanPang/Libra_R-CNN





TuesdayPoster 1.159Jiangmiao Pang

4243D Appearance Super-Resolution With Deep Learninghttps://github.com/ofsoundof/3D_Appearance_SR





ThursdayPoster 3.1104Yawei LiYawei Li, Vagia Tsiminaki, Radu Timofte, Marc Pollefeys, Luc van Gool

58DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationhttps://github.com/Oktosha/DeepSDF-explained?


TuesdayOral 1.1B9:23TuesdayPoster 1.176Jeong Joon ParkJeong Joon Park, Peter Florence, Julian Straub, Richard Newcombe, Steven Lovegrove

425Hybrid Task Cascade for Instance Segmentationhttps://github.com/open-mmlab/mmdetectionhttps://mp.weixin.qq.com/s/xug0xKfc9RgJEUci1a_xog




WednesdayPoster 2.142Kai ChenKai Chen, Jiangmiao Pang, Jiaqi Wang, Yu Xiong, Xiaoxiao Li, Shuyang Sun, Wansen Feng, Ziwei Liu, Jianping Shi, Wanli Ouyang, Chen Change Loy, Dahua Lin

426Region Proposal by Guided Anchoringhttps://github.com/open-mmlab/mmdetectionhttps://mp.weixin.qq.com/s/Sl958JkcJjy-HW9_c-SH4g




TuesdayPoster 1.249Jiaqi WangJiaqi Wang, Kai Chen, Shuo Yang, Chen Change Loy, Dahua Lin

170Learning to Samplehttps://github.com/orendv/learning_to_sample





TuesdayPoster 1.210Oren DovratOren Dovrat, Itai Lang, Shai Avidan

91In Defense of Pre-Trained ImageNet Architectures for Real-Time Semantic Segmentation of Road-Driving Imageshttps://github.com/orsic/swiftnet





ThursdayPoster 3.2202Marin OrsicMarin Or?i?, Ivan Kre?o, Petra Bevandi?, Sini?a ?egvi?

517Unsupervised Learning of Dense Shape Correspondencehttps://github.com/OshriHalimi/unsupervised_learning_of_dense_shape_correspondence


WednesdayOral 2.1A9:29WednesdayPoster 2.111Oshri Halimi

427Translate-to-Recognize Networks for RGB-D Scene Recognitionhttps://github.com/ownstyledu/Translate-to-Recognize-Networks
https://ownstyledu.github.io/Translate-to-Recognize-Networks/



ThursdayPoster 3.288Dapeng DuDu, Dapeng and Wang, Limin and Wang, Huiling and Zhao, Kai and Wu, Gangshan

265Bringing a Blurry Frame Alive at High Frame-Rate With an Event Camerahttps://github.com/panpanfei/Bringing-a-Blurry-Frame-Alive-at-High-Frame-Rate-with-an-Event-Camera


WednesdayOral 2.2C14:06WednesdayPoster 2.2136Liyuan PanLiyuan Pan, Cedric Scheerlinck, Xin Yu, Richard Hartley, Miaomiao Liu, Yuchao Dai

64Feedback Network for Image Super-Resolutionhttps://github.com/Paper99/SRFBN_CVPR19





TuesdayPoster 1.2158Zhen LiZhen Li, Jinglei Yang, Zheng Liu, Xiaomin Yang, Gwanggil Jeon, Wei Wu

167Superquadrics Revisited: Learning 3D Shape Parsing Beyond Cuboidshttps://github.com/paschalidoud/superquadric_parsing





ThursdayPoster 3.1173Despoina PaschalidouDespoina Paschalidou, Ali Osman Ulusoy, Andreas Geiger

428SiamRPN++: Evolution of Siamese Visual Tracking With Very Deep Networkshttps://github.com/PengBoXiangShang/SiamRPN_plus_plus_PyTorchhttps://mp.weixin.qq.com/s/dB5u2No8eakLnrjto0kvyQhttp://bo-li.info/SiamRPN++/
WednesdayOral 2.1A8:35WednesdayPoster 2.12Bo LiBo Li, Wei Wu, Qiang Wang, Fangyi Zhang, Junliang Xing, Junjie Yan

429Representation Flow for Action Recognitionhttps://github.com/piergiaj/representation-flow-cvpr19
https://piergiaj.github.io/rep-flow-site/



ThursdayPoster 3.1132AJ PiergiovanniAJ Piergiovanni, Michael S. Ryoo

266Content Authentication for Neural Imaging Pipelines: End-To-End Optimization of Photo Provenance in Complex Distribution Channelshttps://github.com/pkorus/neural-imaging


ThursdayOral 3.1A9:29ThursdayPoster 3.1200Pawel KorusPawel Korus, Nasir Memon

125Bi-Directional Cascade Network for Perceptual Edge Detectionhttps://github.com/pkuCactus/BDCN





TuesdayPoster 1.2154Jianzhong HeJianzhong He, Shiliang Zhang, Ming Yang, Yanhu Shan, Tiejun Huang

430SelFlow: Self-Supervised Learning of Optical Flowhttps://github.com/ppliuboy/SelFlow


WednesdayOral 2.1C8:30WednesdayPoster 2.1135Pengpeng Liu

190JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds With Multi-Task Pointwise Networks and Multi-Value Conditional Random Fieldshttps://github.com/pqhieu/JSIS3D
https://pqhieu.github.io/cvpr19.html?
ThursdayOral 3.1C8:35ThursdayPoster 3.156Quang-Hieu PhamQuang-Hieu Pham, Duc Thanh Nguyen, Binh-Son Hua, Gemma Roig, Sai-Kit Yeung

431Learning Single-Image Depth From Videos Using Quality Assessment Networkshttps://github.com/princeton-vl/YouTube3D





WednesdayPoster 2.1121Weifeng Chen

432Describing Like Humans: On Diversity in Image Captioninghttps://github.com/qingzwang/DiversityMetrics





TuesdayPoster 1.2209Qingzhong WangQingzhong Wang, Antoni B. Chan

1090Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identificationhttps://github.com/QizeYang/PAUL





TuesdayPoster 1.2116Qize Yang

433Amodal Instance Segmentation With KINS Datasethttps://github.com/qqlu/Amodal-Instance-Segmentation-through-KINS-Dataset





TuesdayPoster 1.254Lu QiLu Qi, Li Jiang, Shu Liu, Xiaoyong Shen, Jiaya Jia

434Information Maximizing Visual Question Generationhttps://github.com/ranjaykrishna/iq





TuesdayPoster 1.1203Ranjay KrishnaKrishna, Ranjay and Bernstein, Michael and Fei-Fei, Li

182Learning Pyramid-Context Encoder Network for High-Quality Image Inpaintinghttps://github.com/researchmm/PEN-Net-for-Inpainting





TuesdayPoster 1.1150Yanhong ZengYanhong Zeng, Jianlong Fu, Hongyang Chao, Baining Guo

39Deeper and Wider Siamese Networks for Real-Time Visual Trackinghttps://github.com/researchmm/SiamDW


WednesdayOral 2.1C8:40WednesdayPoster 2.1137Zhipeng ZhangZhipeng Zhang, Houwen Peng

71Class-Balanced Loss Based on Effective Number of Sampleshttps://github.com/richardaecn/class-balanced-loss





ThursdayPoster 3.133Yin CuiYin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, Serge Belongie

299Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shifthttps://github.com/rileykwok/Food-Classification





TuesdayPoster 1.22Xiang LiXiang Li, Shuo Chen, Xiaolin Hu, Jian Yang

214Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoshttps://github.com/RomeroBarata/skeleton_based_anomaly_detection





ThursdayPoster 3.2122Romero MoraisRomero Morais, Vuong Le, Truyen Tran, Budhaditya Saha, Moussa Mansour, Svetha Venkatesh

37From Recognition to Cognition: Visual Commonsense Reasoninghttps://github.com/rowanz/r2c


WednesdayOral 2.2B14:52WednesdayPoster 2.2191Rowan ZellersRowan Zellers, Yonatan Bisk, Ali Farhadi, Yejin Choi

174Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptationhttps://github.com/RoyalVane/CLAN


TuesdayOral 1.2C13:35TuesdayPoster 1.2167Yawei LuoYawei Luo, Liang Zheng, Tao Guan, Junqing Yu, Yi Yang

435Unsupervised Domain Adaptation Using Feature-Whitening and Consensus Losshttps://github.com/roysubhankar/dwt-domain-adaptation





ThursdayPoster 3.154Subhankar Roy

224Regularizing Activation Distribution for Training Binarized Deep Networkshttps://github.com/ruizhoud/DistributionLoss





ThursdayPoster 3.244Ruizhou DingRuizhou Ding, Ting-Wu Chin, Zeye Liu, Diana Marculescu

436S4Net: Single Stage Salient-Instance Segmentationhttps://github.com/RuochenFan/S4Net





WednesdayPoster 2.1187Ruochen FanRuochen Fan, Ming-Ming Cheng, Qibin Hou, Tai-Jiang Mu, Jingdong Wang, Shi-Min Hu

300Detecting Overfitting of Deep Generative Networks via Latent Recoveryhttps://github.com/ryanwebster90/gen-overfitting-latent-recovery





ThursdayPoster 3.230Ryan WebsterRyan Webster,?Julien Rabin,?Loic Simon,?Frederic Jurie

26ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Networkhttps://github.com/sacmehta/ESPNetv2?





ThursdayPoster 3.125Sachin MehtaSachin Mehta, Mohammad Rastegari, Linda Shapiro, Hannaneh Hajishirzi

274ContactDB: Analyzing and Predicting Grasp Contact via Thermal Imaginghttps://github.com/samarth-robo/contactdb_prediction


ThursdayOral 3.1B8:53ThursdayPoster 3.181Samarth BrahmbhattSamarth Brahmbhatt, Cusuh Ham, Charles C. Kemp, and James Hays

437Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Videohttps://github.com/SamvitJ/Accel


ThursdayOral 3.1C8:58ThursdayPoster 3.160Samvit Jain

255Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learninghttps://github.com/SAP/machine-learning-dgm





ThursdayPoster 3.235Oleksiy OstapenkoOleksiy Ostapenko, Tassilo Klein, Mihai Puscas, Patrick J?hnichen, Moin Nabi

438SOSNet: Second Order Similarity Regularization for Local Descriptor Learninghttps://github.com/scape-research/SOSNet


ThursdayOral 3.2C13:48ThursdayPoster 3.2150Yurun Tian

176DAVANet: Stereo Deblurring With View Aggregationhttps://github.com/sczhou/DAVANet


ThursdayOral 3.2C13:35ThursdayPoster 3.2148Shangchen ZhouShangchen Zhou, Jiawei Zhang, Wangmeng Zuo, Haozhe Xie, Jinshan Pan, Jimmy Ren

161WarpGAN: Automatic Caricature Generationhttps://github.com/seasonSH/WarpGAN


ThursdayOral 3.2A14:52ThursdayPoster 3.215Yichun ShiYichun Shi, Debayan Deb, Anil K. Jain

883D-SIS: 3D Semantic Instance Segmentation of RGB-D Scanshttps://github.com/Sekunde/3D-SIS


WednesdayOral 2.1B8:30WednesdayPoster 2.1106Ji HouJi Hou Angela Dai Matthias Nie?ner

301Understanding and Visualizing Deep Visual Saliency Modelshttps://github.com/SenHe/uavdvsm





ThursdayPoster 3.1159Sen HeSen He, Hamed R. Tavakoli, Ali Borji, Yang Mi, Nicolas Pugeault

302Unsupervised Visual Domain Adaptation: A Deep Max-Margin Gaussian Process Approachhttps://github.com/seqam-lab/GPDA


WednesdayOral 2.1A9:34WednesdayPoster 2.112Minyoung KimMinyoung Kim, Pritish Sahu, Behnam Gholami, Vladimir Pavlovic

225Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortionshttps://github.com/sg-nm/Operation-wise-attention-network





ThursdayPoster 3.19Masanori SuganumaMasanori Suganuma, Xing Liu, Takayuki Okatani

439FSA-Net: Learning Fine-Grained Structure Aggregation for Head Pose Estimation From a Single Imagehttps://github.com/shamangary/FSA-Net





TuesdayPoster 1.198Tsun-Yi YangTsun-Yi Yang, Yi-Ting Chen, Yen-Yu Lin, and Yung-Yu Chuang

256Centripetal SGD for Pruning Very Deep Convolutional Networks With Complicated Structurehttps://github.com/ShawnDing1994/Centripetal-SGD





WednesdayPoster 2.139Xiaohan DingXiaohan Ding, Guiguang Ding, Yuchen Guo, Jungong Han

440Wide-Context Semantic Image Extrapolationhttps://github.com/shepnerd/outpainting_srn





TuesdayPoster 1.1141Yi WangYi Wang, Xin Tao, Xiaoyong Shen, Jiaya Jia.

441Scene Parsing via Integrated Classification Model and Variance-Based Regularizationhttps://github.com/shihengcan/ICM-matcaffe





WednesdayPoster 2.176Hengcan ShiHengcan Shi, Hongliang Li, Qingbo Wu, Zichen Song

139Explainable and Explicit Visual Reasoning Over Scene Graphshttps://github.com/shijx12/XNM-Net





WednesdayPoster 2.2202Jiaxin ShiJiaxin Shi, Hanwang Zhang, Juanzi Li

220MHP-VOS: Multiple Hypotheses Propagation for Video Object Segmentationhttps://github.com/shuangjiexu/MHP-VOS


TuesdayOral 1.1C9:41TuesdayPoster 1.1116Shuangjie XuShuangjie Xu, Daizong Liu, Linchao Bao, Wei Liu, Pan Zhou

153RePr: Improved Training of Convolutional Filtershttps://github.com/siahuat0727/RePr


ThursdayOral 3.2A13:53ThursdayPoster 3.25Aaditya PrakashAaditya Prakash, James Storer, Dinei Florencio, Cha Zhang

510Unsupervised Person Image Generation With Semantic Parsing Transformationhttps://github.com/SijieSong/person_generation_spt


TuesdayOral 1.2B13:53TuesdayPoster 1.2122Sijie Song

191Leveraging Shape Completion for 3D Siamese Trackinghttps://github.com/SilvioGiancola/ShapeCompletion3DTracking





TuesdayPoster 1.1137Silvio GiancolaSilvio Giancola, Jesus Zarzar, Bernard Ghanem

442Learning Non-Volumetric Depth Fusion Using Successive Reprojectionshttps://github.com/simon-donne/defusr





WednesdayPoster 2.291Simon DonneSimon Donné, Andreas Geiger

241Nesti-Net: Normal Estimation for Unstructured 3D Point Clouds Using Convolutional Neural Networkshttps://github.com/sitzikbs/Nesti-Net





ThursdayPoster 3.1149Yizhak Ben-ShabatYizhak Ben-Shabat, Michael Lindenbaum, Anath Fischer

825On Stabilizing Generative Adversarial Training With Noisehttps://github.com/sjenni/dfgan





ThursdayPoster 3.2137Simon Jenni

443Learning Context Graph for Person Searchhttps://github.com/sjtuzq/person_search_gcn


TuesdayOral 1.2A13:40TuesdayPoster 1.220Yichao YanYichao Yan, Qiang Zhang, Bingbing Ni, Wendong Zhang, Minghao Xu, Xiaokang Yang

104Scan2CAD: Learning CAD Model Alignment in RGB-D Scanshttps://github.com/skanti/Scan2CAD


TuesdayOral 1.2C14:42TuesdayPoster 1.2178Armen AvetisyanArmen Avetisyan, Manuel Dahnert, Angela Dai, Manolis Savva, Angel X. Chang, Matthias Nie?ner

444Content-Aware Multi-Level Guidance for Interactive Instance Segmentationhttps://github.com/sm176357/mlg





ThursdayPoster 3.264Soumajit Majumder

226Attention Based Glaucoma Detection: A Large-Scale Database and CNN Modelhttps://github.com/smilell/AG-CNN





ThursdayPoster 3.1211Liu LiLiu Li, Mai Xu, Xiaofei Wang, Lai Jiang, Hanruo Liu

100Parsing R-CNN for Instance-Level Human Analysishttps://github.com/soeaver/Parsing-R-CNN





TuesdayPoster 1.113Lu YangLu Yang, Qing Song, Zhihui Wang, Ming Jiang

275Dynamics Are Important for the Recognition of Equine Pain in Videohttps://github.com/sofiabroome/painface-recognition





ThursdayPoster 3.2208Sofia BroomeSofia Broomé, Karina Bech Gleerup, Pia Haubro Andersen, Hedvig Kjellstr?m

35A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofinghttps://github.com/SoftwareGift/FeatherNets_Face-Anti-spoofing-Attack-Detection-Challenge-CVPR2019





TuesdayPoster 1.169Shifeng ZhangSachin Mehta, Mohammad Rastegari, Linda Shapiro, Hannaneh Hajishirzi

105Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervisionhttps://github.com/soubhiksanyal/RingNet
https://ringnet.is.tue.mpg.de/



WednesdayPoster 2.2104Soubhik SanyalSoubhik Sanyal, Timo Bolkart, Haiwen Feng, Michael J. Black

114Efficient Parameter-Free Clustering Using First Neighbor Relationshttps://github.com/ssarfraz/FINCH-CLustering


ThursdayOral 3.1C9:42ThursdayPoster 3.167Saquib SarfrazM. Saquib Sarfraz, Vivek Sharma, Rainer Stiefelhagen

148Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimationhttps://github.com/sshan-zhao/GASDA





ThursdayPoster 3.1116Shanshan ZhaoShanshan Zhao, Huan Fu, Mingming Gong, Dacheng Tao

33PointRCNN: 3D Object Proposal Generation and Detection From Point Cloudhttps://github.com/sshaoshuai/PointRCNN





TuesdayPoster 1.154Shaoshuai ShiShaoshuai Shi, Xiaogang Wang, Hongsheng Li

444D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkshttps://github.com/StanfordVL/MinkowskiEngine





TuesdayPoster 1.260Christopher ChoyChristopher Choy, JunYoung Gwak, Silvio Savarese

288Generative Dual Adversarial Network for Generalized Zero-Shot Learninghttps://github.com/stevehuanghe/GDAN





TuesdayPoster 1.157He HuangHe Huang, Changhu Wang, Philip S. Yu, Chang-Dong Wang

140Spatial Attentive Single-Image Deraining With a High Quality Real Rain Datasethttps://github.com/stevewongv/SPANet
https://stevewongv.github.io/derain-project.html



ThursdayPoster 3.2168Tianyu WangTianyu Wang*, Xin Yang*, Ke Xu, Shaozhe Chen, Qiang Zhang, Rynson Lau

141Aggregation Cross-Entropy for Sequence Recognitionhttps://github.com/summerlvsong/Aggregation-Cross-Entropy


WednesdayOral 2.2A14:52WednesdayPoster 2.239Zecheng XieZecheng Xie, Yaoxiong Huang, Yuanzhi Zhu, Lianwen Jin, Yuliang Liu, Lele Xie

1211Deeply-Supervised Knowledge Synergyhttps://github.com/sundw2014/DKS





WednesdayPoster 2.27Dawei Sun

445Leveraging Crowdsourced GPS Data for Road Extraction From Aerial Imageryhttps://github.com/suniique/Leveraging-Crowdsourced-GPS-Data-for-Road-Extraction-from-Aerial-Imagery?





WednesdayPoster 2.278Tao SunTao Sun, Zonglin Di, Pengyu Che, Chun Liu, Yin Wang

138HorizonNet: Learning Room Layout With 1D Representation and Pano Stretch Data Augmentationhttps://github.com/sunset1995/HorizonNet
https://sunset1995.github.io/HorizonNet/



TuesdayPoster 1.194Cheng SunCheng Sun, Chi-Wei Hsiao, Min Sun, Hwann-Tzong Chen

94Learning Linear Transformations for Fast Image and Video Style Transferhttps://github.com/sunshineatnoon/LinearStyleTransfer
https://sites.google.com/view/linear-style-transfer-cvpr19/



TuesdayPoster 1.2152Xueting LiXueting Li, Sifei Liu, Jan Kautz, Ming-Hsuan Yang

73Single-Image Piece-Wise Planar 3D Reconstruction via Associative Embeddinghttps://github.com/svip-lab/PlanarReconstruction





TuesdayPoster 1.192Zehao YuZehao Yu, Jia Zheng, Dongze Lian, Zihan Zhou, Shenghua Gao

227PPGNet: Learning Point-Pair Graph for Line Segment Detectionhttps://github.com/svip-lab/PPGNet





WednesdayPoster 2.218Ziheng ZhangZiheng Zhang, Zhengxin Li, Ning Bi, Jia Zheng, Jinlei Wang, Kun Huang, Weixin Luo, Yanyu Xu, Shenghua Gao

17DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Imageshttps://github.com/switchablenorms/DeepFashion2





WednesdayPoster 2.179Yuying GeYuying Ge, Ruimao Zhang, Lingyun Wu, Xiaogang Wang, Xiaoou Tang, Ping Luo

168SSN: Learning Sparse Switchable Normalization via SparsestMaxhttps://github.com/switchablenorms/Sparse_SwitchNorm





TuesdayPoster 1.121Wenqi ShaoWenqi Shao, Tianjian Meng, Jingyu Li, Ruimao Zhang, Yudian Li, Xiaogang Wang, Ping Luo

446Dissecting Person Re-Identification From the Viewpoint of Viewpointhttps://github.com/sxzrt/Dissecting-Person-Re-ID-from-the-Viewpoint-of-Viewpoint





TuesdayPoster 1.138Xiaoxiao SunTing Zhao, Xiangqian Wu

447Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring Transformationhttps://github.com/taki0112/GDWCT-Tensorflow


ThursdayOral 3.2A13:35ThursdayPoster 3.22Wonwoong ChoWonwoong Cho, Sungha Choi, David Keetae Park, Inkyu Shin, Jaegul Choo

448Sphere Generative Adversarial Network Based on Geometric Moment Matchinghttps://github.com/taki0112/SphereGAN-Tensorflow?


WednesdayOral 2.1A8:40WednesdayPoster 2.13Sung Woo ParkSung Woo Park and Junseok Kwon

578Label-Noise Robust Generative Adversarial Networkshttps://github.com/takuhirok/rGAN


TuesdayOral 1.2B15:00TuesdayPoster 1.2133Takuhiro Kaneko

617A Skeleton-Bridged Deep Learning Approach for Generating Meshes of Complex Topologies From Single RGB Imageshttps://github.com/tangjiapeng/SkeletonBridgeRecon


WednesdayOral 2.1B9:42WednesdayPoster 2.1118Jiapeng Tang

289Defending Against Adversarial Attacks by Randomized Diversificationhttps://github.com/taranO/defending-adversarial-attacks-by-RD





ThursdayPoster 3.225Olga TaranO. Taran, S. Rezaeifar, T. Holotyak, and S. Voloshynovskiy

257Model-Blind Video Denoising via Frame-To-Frame Traininghttps://github.com/tehret/blind-denoising





ThursdayPoster 3.240Thibaud EhretThibaud Ehret, Axel Davy, Jean-Michel Morel, Gabriele Facciolo, Pablo Arias

8DSFD: Dual Shot Face Detectorhttps://github.com/TencentYoutuResearch/FaceDetection-DSFDhttps://mp.weixin.qq.com/s/0rTCeHumVSv07hMCaCd7EA




WednesdayPoster 2.151Jian LiJian Li, Yabiao Wang, Changan Wang, Ying Tai

47Progressive Pose Attention Transfer for Person Image Generationhttps://github.com/tengteng95/Pose-Transfer


TuesdayOral 1.2B13:48TuesdayPoster 1.2121Zhen ZhuZhen Zhu, Tengteng Huang, Baoguang Shi, Miao Yu, Bofei Wang, Xiang Bai

1Detect-To-Retrieve: Efficient Regional Aggregation for Image Searchhttps://github.com/tensorflow/models/tree/master/research/delf

Retrieve


WednesdayPoster 2.156Marvin TeichmannMarvin Teichmann, Andre Araujo, Menglong Zhu, Jack Sim

1247FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentationhttps://github.com/tensorflow/models/tree/master/research/feelvos





ThursdayPoster 3.170Paul Voigtlaender

27MnasNet: Platform-Aware Neural Architecture Search for Mobilehttps://github.com/tensorflow/tpu/tree/master/models/official/mnasnet





TuesdayPoster 1.216Mingxing TanMingxing Tan,?Bo Chen,?Ruoming Pang,?Vijay Vasudevan,?Mark Sandler,?Andrew Howard,?Quoc V. Le

122Learning to Reconstruct People in Clothing From a Single RGB Camerahttps://github.com/thmoa/octopus





TuesdayPoster 1.1107Thiemo AlldieckThiemo Alldieck, Marcus Magnor, Bharat Lal Bhatnagar, Christian Theobalt, Gerard Pons-Moll

449Learning to Transfer Examples for Partial Domain Adaptationhttps://github.com/thuml/ETN





TuesdayPoster 1.251Zhangjie CaoZhangjie Cao, Kaichao You, Mingsheng Long, Jianmin Wang, Qiang Yang

450Universal Domain Adaptationhttps://github.com/thuml/Universal-Domain-Adaptation?





TuesdayPoster 1.26Kaichao YouKaichao You, Mingsheng Long, Zhangjie Cao, Jianmin Wang, and Michael . Jordan

451Multispectral Imaging for Fine-Grained Recognition of Powders on Complex Backgroundshttps://github.com/tiancheng-zhi/ms-powder
http://www.cs.cmu.edu/~ILIM/projects/IM/MSPowder/?
ThursdayOral 3.1B8:48ThursdayPoster 3.180Tiancheng ZhiTiancheng Zhi, Bernardo R. Pires, Martial Hebert and Srinivasa G. Narasimhan

290On the Continuity of Rotation Representations in Neural Networkshttps://github.com/tik0/6d





WednesdayPoster 2.1150Yi ZhouYi Zhou, Connelly Barnes, Jingwan Lu, Jimei Yang, Hao Li

126Capture, Learning, and Synthesis of 3D Speaking Styleshttps://github.com/TimoBolkart/voca





ThursdayPoster 3.1148Daniel CudeiroDaniel Cudeiro, Timo Bolkart, Cassidy Laidlaw, Anurag Ranjan, Michael J. Black

585Deep Metric Learning Beyond Binary Supervisionhttps://github.com/tjddus9597/Beyond-Binary-Supervision-CVPR19


TuesdayOral 1.2A15:00TuesdayPoster 1.233Sungyeon Kim

571Probabilistic Permutation Synchronization Using the Riemannian Structure of the Birkhoff Polytopehttps://github.com/tolgabirdal/birkhoffrlmc


ThursdayOral 3.2C14:42ThursdayPoster 3.2159Tolga BirdalTolga Birdal & Umut _im_ekli

281On Zero-Shot Recognition of Generic Objectshttps://github.com/TristHas/GOZ





ThursdayPoster 3.192Tristan HascoetTristan Hascoet, Yasuo Ariki, Tetsuya Takiguchi

276Distilling Object Detectors With Fine-Grained Feature Imitationhttps://github.com/twangnh/Distilling-Object-Detectors





WednesdayPoster 2.138Tao WangTao Wang,Li Yuan,Xiaopeng Zhang,Jiashi Feng

215Elastic Boundary Projection for 3D Medical Image Segmentationhttps://github.com/twni2016/Elastic-Boundary-Projection





TuesdayPoster 1.1213Tianwei NiTianwei Ni, Lingxi Xie, Huangjie Zheng, Elliot K. Fishman, Alan L. Yuille

228Reversible GANs for Memory-Efficient Image-To-Image Translationhttps://github.com/tychovdo/RevGAN





WednesdayPoster 2.116Tycho F.A. van der OuderaaTycho F.A. van der Ouderaa, Daniel E. Worrall

452Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networkshttps://github.com/tyohei/chainerkfac





ThursdayPoster 3.2177Kazuki OsawaKazuki Osawa, Yohei Tsuji, Yuichiro Ueno, Akira Naruse, Rio Yokota, and Satoshi Matsuoka

48UPSNet: A Unified Panoptic Segmentation Networkhttps://github.com/uber-research/UPSNet


ThursdayOral 3.1C8:30ThursdayPoster 3.155Yuwen Xionguwen Xiong, Renjie Liao, Hengshuang Zhao, Rui Hu, Min Bai, Ersin Yumer, Raquel Urtasun

131Hierarchical Discrete Distribution Decomposition for Match Density Estimationhttps://github.com/ucbdrive/hd3





WednesdayPoster 2.1181Zhichao YinZhichao Yin, Trevor Darrell, Fisher Yu

453TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learninghttps://github.com/ucbdrive/tafe-net





TuesdayPoster 1.1185Xin WangXin Wang, Fisher Yu, Ruth Wang, Trevor Darrell, Joseph E. Gonzalez

454Text2Scene: Generating Compositional Scenes From Textual Descriptionshttps://github.com/uvavision/Text2Image?


WednesdayOral 2.2B14:47WednesdayPoster 2.2190Fuwen TanYitong Li, Zhe Gan, Yelong Shen, Jingjing Liu, Yu Cheng, Yuexin Wu, Lawrence Carin, David Carlson, Jianfeng Gao

209ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationhttps://github.com/valeoai/ADVENT


TuesdayOral 1.2C13:40TuesdayPoster 1.2168Tuan-Hung VuTuan-Hung Vu, Himalaya Jain, Maxime Bucher, Matthieu Cord, Patrick Pérez

154Single Image Reflection Removal Exploiting Misaligned Training Data and Network Enhancementshttps://github.com/Vandermode/ERRNet





WednesdayPoster 2.2164Kaixuan WeiKaixuan Wei, Jiaolong Yang, Ying Fu, David Wipf, Hua Huang

455Expressive Body Capture: 3D Hands, Face, and Body From a Single Imagehttps://github.com/vchoutas/smplify-x
https://smpl-x.is.tue.mpg.de/?
ThursdayOral 3.2B15:10ThursdayPoster 3.2109Georgios PavlakosGeorgios Pavlakos, Vasileios Choutas, Nima Ghorbani, Timo Bolkart, Ahmed A. A. Osman, Dimitrios Tzionas, Michael J. Black

456C3AE: Exploring the Limits of Compact Model for Age Estimationhttps://github.com/vicwer/C3AE_Age_Estimation





ThursdayPoster 3.2200Chao ZhangChao Zhang, Shuaicheng Liu, Xun Xu, Ce Zhu

258Weakly Supervised Deep Image Hashing Through Tag Embeddingshttps://github.com/Vijetha1/WDHT





ThursdayPoster 3.1176Vijetha GattupalliVijetha Gattupalli, Yaoxin Zhuo, Baoxin Li

291Actor-Critic Instance Segmentationhttps://github.com/visinf/acis





WednesdayPoster 2.2170Nikita AraslanovKwang In Kim, Hyung Jin Chang

457Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimationhttps://github.com/visinf/irr





WednesdayPoster 2.1151Junhwa HurJunhwa Hur and Stefan Roth

99Strong-Weak Distribution Alignment for Adaptive Object Detectionhttps://github.com/VisionLearningGroup/DA_Detection





WednesdayPoster 2.23Kuniaki SaitoKuniaki Saito, Yoshitaka Ushiku, Tatsuya Harada, Kate Saenko

22ATOM: Accurate Tracking by Overlap Maximizationhttps://github.com/visionml/pytracking


WednesdayOral 2.1C9:24WednesdayPoster 2.1144Martin DanelljanMartin Danelljan, Goutam Bhat, Fahad Shahbaz Khan, Michael Felsberg

458MOTS: Multi-Object Tracking and Segmentationhttps://github.com/VisualComputingInstitute/mots_tools





WednesdayPoster 2.2122Paul Voigtlaender

45PifPaf: Composite Fields for Human Pose Estimationhttps://github.com/vita-epfl/openpifpaf





ThursdayPoster 3.2120Sven KreissSven Kreiss, Lorenzo Bertoni, Alexandre Alahi

459Mixed Effects Neural Networks (MeNets) With Applications to Gaze Estimationhttps://github.com/vsingh-group/MeNets





WednesdayPoster 2.2102Yunyang Xiong

175Curls & Whey: Boosting Black-Box Adversarial Attackshttps://github.com/walegahaha/Curls-Whey


WednesdayOral 2.2A14:42WednesdayPoster 2.237Yucheng ShiYucheng Shi, Siyu Wang, Yahong Han

115Adaptively Connected Neural Networkshttps://github.com/wanggrun/Adaptively-Connected-Neural-Networks





TuesdayPoster 1.1180Guangrun WangGuangrun Wang, Keze Wang, Liang Lin

513Shape2Motion: Joint Analysis of Motion Parts and Attributes From 3D Shapeshttps://github.com/wangxiaogang866/Shape2Motion


ThursdayOral 3.1C9:06ThursdayPoster 3.161Xiaogang Wang

460Interactive Image Segmentation via Backpropagating Refinement Schemehttps://github.com/wdjang/BRS-Interactive_segmentation





WednesdayPoster 2.175Won-Dong JangWon-Dong Jang and Chang-Su Kim

250Iterative Reorganization With Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation Learninghttps://github.com/weichen582/Unsupervised-Visual-Recognition-by-Solving-Arbitrary-Puzzles





TuesdayPoster 1.1193Chen WeiChen Wei, Lingxi Xie, Xutong Ren, Yingda Xia, Chi Su, Jiaying Liu, Qi Tian, Alan L. Yuille

221Conditional Single-View Shape Generation for Multi-View Stereo Reconstructionhttps://github.com/weiyithu/OptimizeMVS





ThursdayPoster 3.1102Yi WeiYi Wei, Shaohui Liu, Wang Zhao, Jiwen Lu, Jie Zhou

461Revisiting Local Descriptor Based Image-To-Class Measure for Few-Shot Learninghttps://github.com/WenbinLee/DN4.git





WednesdayPoster 2.252Wenbin LiWenbin Li, Lei Wang, Jinglin Xu, Jing Huo, Yang Gao, Jiebo Luo

777Learning Unsupervised Video Object Segmentation Through Visual Attentionhttps://github.com/wenguanwang/AGS





TuesdayPoster 1.259Wenguan Wang

462Adapting Object Detectors via Selective Cross-Domain Alignmenthttps://github.com/WERush/SCDA





TuesdayPoster 1.146Xinge ZhuZhu, Xinge and Pang, Jiangmiao and Yang, Ceyuan and Shi, Jianping and Lin, Dahua

24Shape Robust Text Detection With Progressive Scale Expansion Networkhttps://github.com/whai362/PSENet





ThursdayPoster 3.140Wenhai WangXiang Li, Wenhai Wang, Wenbo Hou, Ruo-Ze Liu, Tong Lu, Jian Yang

498AE2-Nets: Autoencoder in Autoencoder Networkshttps://github.com/willow617/AE2-Nets


TuesdayOral 1.2C14:16TuesdayPoster 1.2174Changqing ZhangChangqing Zhang ,Yeqing Liu, Huazhu Fu

229C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detectionhttps://github.com/Winfrand/C-MIL


TuesdayOral 1.2A14:06TuesdayPoster 1.224Fang WanFang Wan, Chang Liu, Wei Ke, Xiangyang Ji, Jianbin Jiao, Qixiang Ye

204Learning Actor Relation Graphs for Group Activity Recognitionhttps://github.com/wjchaoGit/Group-Activity-Recognition





ThursdayPoster 3.1134Jianchao WuJianchao Wu, Limin Wang, Li Wang, Jie Guo, Gangshan Wu

463Multi-Task Self-Supervised Object Detection via Recycling of Bounding Box Annotationshttps://github.com/wonheeML/mtl-ssl





WednesdayPoster 2.143Wonhee Lee

149Cascaded Partial Decoder for Fast and Accurate Salient Object Detectionhttps://github.com/wuzhe71/CPD





TuesdayPoster 1.2162Zhe WuZhe Wu, Li Su, Qingming Huang

65Associatively Segmenting Instances and Semantics in Point Cloudshttps://github.com/WXinlong/ASIS





TuesdayPoster 1.2199Xinlong WangXinlong Wang, Shu Liu, Xiaoyong Shen, Chunhua Shen, Jiaya Jia

77Hardness-Aware Deep Metric Learninghttps://github.com/wzzheng/HDML


TuesdayOral 1.1A9:41TuesdayPoster 1.18Wenzhao ZhengWenzhao Zheng, Zhaodong Chen, Jiwen Lu, Jie Zhou

67Data Augmentation Using Learned Transformations for One-Shot Medical Image Segmentationhttps://github.com/xamyzhao/brainstorm


ThursdayOral 3.1A8:40ThursdayPoster 3.1192Amy ZhaoAmy Zhao,?Guha Balakrishnan,?Frédo Durand,?John V. Guttag,?Adrian V. Dalca

464Synthesizing Environment-Aware Activities via Activity Sketcheshttps://github.com/xavierpuigf/virtualhome





WednesdayPoster 2.1206Yuan-Hong LiaoA. Liao*, X. Puig*, M. Boben, A. Torralba, S. Fidler

465Generating 3D Adversarial Point Cloudshttps://github.com/xiangchong1/3d-adv-pc





ThursdayPoster 3.119Chong XiangChong Xiang, Charles R. Qi , Bo Li

142Learning Transformation Synchronizationhttps://github.com/xiangruhuang/Learning2Sync





WednesdayPoster 2.2154Xiangru HuangXiangru Huang, Zhenxiao Liang, Xiaowei Zhou, Yao Xie, Leonidas Guibas, and Qixing Huang

466Self-Supervised Learning via Conditional Motion Propagationhttps://github.com/XiaohangZhan/conditional-motion-propagation?





TuesdayPoster 1.1190Xiaohang ZhanXiaohang Zhan, Xingang Pan, Ziwei Liu, Dahua Lin, Chen Change Loy

72AOGNets: Compositional Grammatical Architectures for Deep Learninghttps://github.com/xilaili/AOGNet





WednesdayPoster 2.1199Xilai LiXilai Li,?Xi Song,?Tianfu Wu

18Bottom-Up Object Detection by Grouping Extreme and Center Pointshttps://github.com/xingyizhou/ExtremeNet





TuesdayPoster 1.162Xingyi ZhouXingyi Zhou, Jiacheng Zhuo, Philipp Kr?henbühl

467Learning Video Representations From Correspondence Proposalshttps://github.com/xingyul/cpnet


WednesdayOral 2.1A8:30WednesdayPoster 2.11Xingyu LiuXingyu Liu, Joon-Young Lee and Hailin Jin

468FlowNet3D: Learning Scene Flow in 3D Point Cloudshttps://github.com/xingyul/flownet3d





TuesdayPoster 1.130Xingyu LiuXingyu Liu, Charles R. Qi, Leonidas J. Guibas

469Target-Aware Deep Trackinghttps://github.com/XinLi-zn/TADT
https://xinli-zn.github.io/TADT-project-page/



TuesdayPoster 1.1138Xin LiXin Li, Chao Ma, Baoyuan Wu, Zhenyu He, Ming-Hsuan Yang

1242Deep Network Interpolation for Continuous Imagery Effect Transitionhttps://github.com/xinntao/DNI





TuesdayPoster 1.1171Xintao Wang

470Ranked List Loss for Deep Metric Learninghttps://github.com/XinshaoAmosWang/Deep-Metric-Embedding





WednesdayPoster 2.166Xinshao Wang

267PCAN: 3D Attention Map Learning Using Contextual Information for Point Cloud Based Retrievalhttps://github.com/XLechter/PCAN





ThursdayPoster 3.2185Wenxiao ZhangWenxiao Zhang, Chunxia Xiao

277IP102: A Large-Scale Benchmark Dataset for Insect Pest Recognitionhttps://github.com/xpwu95/IP102


ThursdayOral 3.1B9:42ThursdayPoster 3.189Xiaoping WuXiaoping Wu,Chi Zhan,Yu-Kun Lai,Ming-Ming Cheng,Jufeng Yang

169Rob-GAN: Generator, Discriminator, and Adversarial Attackerhttps://github.com/xuanqing94/RobGAN





ThursdayPoster 3.226Xuanqing LiuXuanqing Liu, Cho-Jui Hsieh

471Self-Supervised Spatiotemporal Learning via Video Clip Order Predictionhttps://github.com/xudejing/VCOP





ThursdayPoster 3.1172Dejing XuDejing Xu,Jun Xiao,Zhou Zhao,Jian Shao,Di Xie,Yueting Zhuang

472Meta-SR: A Magnification-Arbitrary Network for Super-Resolutionhttps://github.com/XuecaiHu/Meta-SR-Pytorch





TuesdayPoster 1.1159Xuecai HuXuecai Hu, Haoyuan Mu, Xiangyu Zhang, Zilei Wang, Tieniu Tan, Jian Sun

473Depth-Attentional Features for Single-Image Rain Removalhttps://github.com/xw-hu/DAF-Net





WednesdayPoster 2.2148Xiaowei HuXiaowei Hu, Chi-Wing Fu, Lei Zhu, and Pheng-Ann Heng

102Group-Wise Correlation Stereo Networkhttps://github.com/xy-guo/GwcNet





TuesdayPoster 1.280Xiaoyang GuoXiaoyang Guo, Kai Yang, Wukui Yang, Xiaogang Wang, Hongsheng Li

133Meta-Transfer Learning for Few-Shot Learninghttps://github.com/y2l/meta-transfer-learning-tensorflow





TuesdayPoster 1.117Qianru SunQianru Sun, Yaoyao Liu, Tat-Seng Chua, Bernt Schiele

199MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentationhttps://github.com/yabufarha/ms-tcn





TuesdayPoster 1.2110Yazan Abu FarhaYazan Abu Farha, Juergen Gall

474Polysemous Visual-Semantic Embedding for Cross-Modal Retrievalhttps://github.com/yalesong/pvse





TuesdayPoster 1.1200Yale Song

519Auto-Encoding Scene Graphs for Image Captioninghttps://github.com/yangxuntu/SGAE


ThursdayOral 3.2A14:06ThursdayPoster 3.27Xu Yang

292On Finding Gray Pixelshttps://github.com/yanlinqian/Grayness-Index





WednesdayPoster 2.2152Yanlin QianYanlin Qian, Joni-Kristian K?m?r?inen, Jarno Nikkanen, Jiri Matas

124Video Relationship Reasoning Using Gated Spatio-Temporal Energy Graphhttps://github.com/yaohungt/GSTEG_CVPR_2019





ThursdayPoster 3.1181Yao-Hung Hubert TsaiYao-Hung Hubert Tsai, Santosh Divvala, Louis-Philippe Morency, Ruslan Salakhutdinov, Ali Farhadi

200What Object Should I Use? - Task Driven Object Detectionhttps://github.com/yassersouri/task-driven-object-detection





WednesdayPoster 2.288Johann SawatzkyJohann Sawatzky, Yaser Souri, Christian Grund, Juergen Gall

475InverseRenderNet: Learning Single Image Inverse Renderinghttps://github.com/YeeU/InverseRenderNet





TuesdayPoster 1.268Ye YuYu, Ye and Smith, William AP

143Patch-Based Progressive 3D Point Set Upsamplinghttps://github.com/yifita/3PU





WednesdayPoster 2.1172Wang YifanWang Yifan, Shihao Wu, Hui Huang, Daniel Cohen-Or, Olga Sorkine-Hornung

32Bounding Box Regression With Uncertainty for Accurate Object Detectionhttps://github.com/yihui-he/KL-Losshttps://mp.weixin.qq.com/s/1q_DZ_-WswjAsS1qjxvLNg?




TuesdayPoster 1.241Yihui HeYihui He, Chenchen Zhu, Jianren Wang, Marios Savvides, Xiangyu Zhang

476Im2Pencil: Controllable Pencil Illustration From Photographshttps://github.com/Yijunmaverick/Im2Pencil?





TuesdayPoster 1.1154Yijun LiYijun Li,Chen Fang, Aaron Hertzmann, Eli Shechtman, Ming-Hsuan Yang

477Probabilistic End-To-End Noise Correction for Learning With Noisy Labelshttps://github.com/yikun2019/PENCIL





WednesdayPoster 2.29Kun Yi

478Homomorphic Latent Space Interpolation for Unpaired Image-To-Image Translationhttps://github.com/yingcong/HomoInterpGAN


TuesdayOral 1.2B14:24TuesdayPoster 1.2127Ying-Cong Chen

303Unsupervised Deep Epipolar Flow for Stationary or Dynamic Sceneshttps://github.com/yiranzhong/EPIflow.git





ThursdayPoster 3.2132Yiran ZhongYiran Zhong, Pan Ji, Jianyuan Wang, Yuchao Dai, Hongdong Li

479StoryGAN: A Sequential Conditional GAN for Story Visualizationhttps://github.com/yitong91/StoryGAN





WednesdayPoster 2.1210Yitong LiYitong Li, Zhe Gan, Yelong Shen, Jingjing Liu, Yu Cheng, Yuexin Wu, Lawrence Carin, David Carlson, Jianfeng Gao

480Learning to Cluster Faces on an Affinity Graphhttps://github.com/yl-1993/learn-to-cluster?


TuesdayOral 1.2A15:05TuesdayPoster 1.234Lei YangLei Yang, Xiaohang Zhan, Dapeng Chen, Junjie Yan, Chen Change Loy, Dahua Lin

95Relation-Shape Convolutional Neural Network for Point Cloud Analysishttps://github.com/Yochengliu/Relation-Shape-CNNhttps://mp.weixin.qq.com/s/KuoHFPpUYHPFacsBWZWVSghttps://yochengliu.github.io/Relation-Shape-CNN/
ThursdayOral 3.1C9:16ThursdayPoster 3.163Yongcheng LiuYongcheng Liu, Bin Fan, Shiming Xiang, Chunhong Pan

1783D Point Capsule Networkshttps://github.com/yongheng1991/3D-point-capsule-networks





TuesdayPoster 1.190Yongheng ZhaoYongheng Zhao, Tolga Birdal, Haowen Deng, Federico Tombari

29Recurrent MVSNet for High-Resolution Multi-View Stereo Depth Inferencehttps://github.com/YoYo000/MVSNet





WednesdayPoster 2.198Yao YaoYao Yao, Zixin Luo, Shiwei Li, Tianwei Shen, Tian Fang, Long Quan

481Side Window Filteringhttps://github.com/YuanhaoGong/SideWindowFilter


ThursdayOral 3.1B9:24ThursdayPoster 3.186Hui YinHui Yin, Yuanhao Gong, Guoping Qiu

86Fast Human Pose Estimationhttps://github.com/yuanyuanli85/Fast_Human_Pose_Estimation_Pytorch





TuesdayPoster 1.2104Feng ZhangFeng Zhang, Xiatian Zhu, Mao Ye

259Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compressionhttps://github.com/yuchaoli/KSE





TuesdayPoster 1.214Yuchao LiYuchao Li, Shaohui Lin, Baochang Zhang, Jianzhuang Liu, David Doermann, Yongjian Wu, Feiyue Huang, Rongrong Ji

482Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachhttps://github.com/yuhuayc/gio-ada





TuesdayPoster 1.1186Yuhua Chen

268RENAS: Reinforced Evolutionary Neural Architecture Searchhttps://github.com/yukang2017/RENAS





WednesdayPoster 2.123Yukang ChenYukang Chen, Gaofeng Meng, Qian Zhang, Shiming Xiang, Chang Huang, Lisen Mu, Xinggang Wang

260DeepFlux for Skeletons in the Wildhttps://github.com/YukangWang/DeepFlux





WednesdayPoster 2.174Yukang WangYukang Wang, Yongchao Xu, Stavros Tsogkas, Xiang Bai, Sven Dickinson, Kaleem Siddiqi

483Recursive Visual Attention in Visual Dialoghttps://github.com/yuleiniu/rva


WednesdayOral 2.2B14:29WednesdayPoster 2.2187Yulei NiuYulei Niu, Hanwang Zhang, Manli Zhang, Jianhong Zhang, Zhiwu Lu, Ji-Rong Wen

97Tightness-Aware Evaluation Protocol for Scene Text Detectionhttps://github.com/Yuliang-Liu/TIoU-metric





ThursdayPoster 3.198Yuliang LiuYuliang Liu, Lianwen Jin, Zecheng Xie, Canjie Luo, Shuaitao Zhang, Lele Xie

158Learning Metrics From Teachers: Compact Networks for Image Embeddinghttps://github.com/yulu0724/EmbeddingDistillation





TuesdayPoster 1.243Lu YuLu Yu, Vacit Oguz Yazici, Xialei Liu, Joost van de Weijer, Yongmei Cheng, Arnau Ramisa

210Memory in Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity From Spatiotemporal Dynamicshttps://github.com/Yunbo426/MIM





ThursdayPoster 3.121Yunbo WangYunbo Wang, Jianjin Zhang, Hongyu Zhu, Mingsheng Long, Jianmin Wang, Philip S Yu

484Connecting Touch and Vision via Cross-Modal Predictionhttps://github.com/YunzhuLi/VisGel
http://visgel.csail.mit.edu/



ThursdayPoster 3.1215Yunzhu LiYunzhu Li,Jun-Yan Zhu,Russ Tedrake,and Antonio Torralba

171Knowledge-Embedded Routing Network for Scene Graph Generationhttps://github.com/yuweihao/KERN





WednesdayPoster 2.1193Tianshui ChenTianshui Chen, Weihao Yu, Riquan Chen, Liang Lin

183Fast Single Image Reflection Suppression via Convex Optimizationhttps://github.com/yyhz76/reflectSuppress





WednesdayPoster 2.2160Yang YangYang Yang, Wenye Ma, Yin Zheng, Jian-Feng Cai, Weiyu Xu

485Path-Invariant Map Networkshttps://github.com/zaiweizhang/path_invariance_map_network


ThursdayOral 3.2C14:29ThursdayPoster 3.2157Zaiwei ZhangZaiwei Zhang, Zhenxiao Liang, Lemeng Wu, Xiaowei Zhou and Qixing Huang

238Multi-Source Weak Supervision for Saliency Detectionhttps://github.com/zengxianyu/mws





WednesdayPoster 2.1184Yu ZengYu Zeng, Yunzhi Zhuge, Huchuan Lu, Lihe Zhang, Mingyang Qian, Yizhou Yu

760Triangulation Learning Network: From Monocular to Stereo 3D Object Detectionhttps://github.com/Zengyi-Qin/TLNet





WednesdayPoster 2.289Zengyi Qin

193A Bayesian Perspective on the Deep Image Priorhttps://github.com/ZezhouCheng/GP-DIP





WednesdayPoster 2.190Zezhou ChengZezhou Cheng, Matheus Gadelha, Subhransu Maji, Daniel Sheldon

486CRAVES: Controlling Robotic Arm With a Vision-Based Economic Systemhttps://github.com/zfw1226/craves_control





TuesdayPoster 1.2211Yiming ZuoZuo, Yiming and Qiu, Weichao and Xie, Lingxi and Zhong, Fangwei and Wang, Yizhou and Yuille, Alan L

136The Perfect Match: 3D Point Cloud Matching With Smoothed Densitieshttps://github.com/zgojcic/3DSmoothNet





WednesdayPoster 2.1100Zan GojcicZan Gojcic, Caifa Zhou, Jan D. Wegner, Andreas Wieser

487CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detectionhttps://github.com/zhangludl/code-and-dataset-for-CapSal?





WednesdayPoster 2.1179Lu ZhangLu Zhang; Huchuan Lu ; Zhe Lin ; Jianming Zhang; You He

488Image Generation From Layouthttps://github.com/zhaobozb/layout2im


ThursdayOral 3.1A9:06ThursdayPoster 3.1196Bo ZhaoBo Zhao, Lili Meng,Weidong Yin, Leonid Sigal

489Learning Spatio-Temporal Representation With Local and Global Diffusionhttps://github.com/ZhaofanQiu/local-and-global-diffusion-networks





ThursdayPoster 3.2128Zhaofan Qiu

230Tracking by Animation: Unsupervised Learning of Multi-Object Attentive Trackershttps://github.com/zhen-he/tracking-by-animation





TuesdayPoster 1.1133Zhen HeZhen He, Jian Li, Daxue Liu, Hangen He, David Barber

278Activity Driven Weakly Supervised Object Detectionhttps://github.com/zhenheny/ADWSOD





TuesdayPoster 1.244Zhenheng YangZhenheng Yang, Dhruv Mahajan, Deepti Ghadiyaram, Ram Nevatia, Vignesh Ramanathan

490Extreme Relative Pose Estimation for RGB-D Scans via Scene Completionhttps://github.com/zhenpeiyang/RelativePose


WednesdayOral 2.1B9:34WednesdayPoster 2.1117Zhenpei YangZhenpei Yang, Jeffrey Z.Pan, Linjie Luo, Xiaowei Zhou, Kristen Grauman and Qixing Huang

491Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensionshttps://github.com/ZhilZheng/Lr-LiVAE





ThursdayPoster 3.2142Zhilin ZhengZhilin Zheng, Li Sun

492Large-Scale Long-Tailed Recognition in an Open Worldhttps://github.com/zhmiao/OpenLongTailRecognition-OLTR
https://liuziwei7.github.io/projects/LongTail.html
TuesdayOral 1.2C13:53TuesdayPoster 1.2170Ziwei LiuZiwei Liu*, Zhongqi Miao*, Xiaohang Zhan, Jiayun Wang, Boqing Gong, Stella X. Yu

116Linkage Based Face Clustering via Graph Convolution Networkhttps://github.com/Zhongdao/gcn_clustering





TuesdayPoster 1.1101Zhongdao WangZhongdao Wang, Liang Zheng, Yali Li, Shengjin Wang

493Unequal-Training for Deep Face Recognition With Long-Tailed Noisy Datahttps://github.com/zhongyy/Unequal-Training-for-Deep-Face-Recognition-with-Long-Tailed-Noisy-Data





WednesdayPoster 2.2109Yaoyao ZhongYaoyao Zhong, Weihong Deng,Mei Wang, Jiani Hu,Jianteng Peng, Xunqiang Tao, Yaohai Huang

66Detailed Human Shape Estimation From a Single Image by Hierarchical Mesh Deformationhttps://github.com/zhuhao-nju/hmd


WednesdayOral 2.1B9:11WednesdayPoster 2.1113Hao ZhuHao Zhu, Xinxin Zuo, Sen Wang, Xun Cao, Ruigang Yang

61Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identificationhttps://github.com/zhunzhong07/ECN





TuesdayPoster 1.137Zhun ZhongZhun Zhong, Liang Zheng, Zhiming Luo, Shaozi Li, Yi Yang

107Disentangled Representation Learning for 3D Face Shapehttps://github.com/zihangJiang/DR-Learning-for-3D-Face





ThursdayPoster 3.2118Zi-Hang JiangZi-Hang Jiang, Qianyi Wu, Keyu Chen, Juyong Zhang

177Reasoning Visual Dialogs With Structural and Partial Observationshttps://github.com/zilongzheng/visdial-gnn


WednesdayOral 2.2B14:24WednesdayPoster 2.2186Zilong ZhengZilong Zheng, Wenguan Wang, Siyuan Qi, Song-Chun Zhu

372Robust Point Cloud Based Reconstruction of Large-Scale Outdoor Sceneshttps://github.com/ziquan111/RobustPCLReconstruction





ThursdayPoster 3.1106Ziquan LanZiquan Lan, Zi Jian Yew,Gim Hee Lee

12Mask Scoring R-CNNhttps://github.com/zjhuang22/maskscoring_rcnnhttps://mp.weixin.qq.com/s/aP7O7AF6WoynWK_FFHkOTw

WednesdayOral 2.2A13:35WednesdayPoster 2.226Zhaojin HuangZhaojin Huang, Lichao Huang, Yongchao Gong, Chang Huang, Xinggang Wang

494Fast and Robust Multi-Person 3D Pose Estimation From Multiple Viewshttps://github.com/zju-3dv/mvpose





WednesdayPoster 2.2107Junting DongJunting Dong, Wen Jiang, Qixing Huang, Hujun Bao, Xiaowei Zhou

42PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimationhttps://github.com/zju3dv/pvnet


WednesdayOral 2.1B9:52WednesdayPoster 2.1120Sida PengSida Peng, Yuan Liu, Qixing Huang, Hujun Bao, and Xiaowei Zhou

51Image Super-Resolution by Neural Texture Transferhttps://github.com/ZZUTK/SRNTT
http://web.eecs.utk.edu/~zzhang61/project_page/SRNTT/SRNTT.html



WednesdayPoster 2.2126Zhifei ZhangZhifei Zhang, Zhaowen Wang, Zhe Lin, Hairong Qi

979TransGaGa: Geometry-Aware Unsupervised Image-To-Image Translationhttps://wywu.github. io/projects/TGaGa/TGaGa.html





WednesdayPoster 2.2129Wayne Wu

495Parallel Optimal Transport GAN



WednesdayOral 2.1A9:52WednesdayPoster 2.115Gil Avraham

496Learning to Explain With Complemental Examples



ThursdayOral 3.1A9:16ThursdayPoster 3.1198Atsushi KanehiraAtsushi Kanehira, Tatsuya Harada

497Textured Neural Avatars



TuesdayOral 1.2B14:11TuesdayPoster 1.2125Aliaksandra ShysheyaAliaksandra Shysheya (Samsung AI Center, Skolkovo Institute of Science and Technology), Egor Zakharov (Samsung AI Center, Skolkovo Institute of Science and Technology), Kara-Ali Aliev (Samsung AI Center), Renat Bashirov (Samsung AI Center), Egor Burkov (Samsung AI Center, Skolkovo Institute of Science and Technology), Karim Iskakov (Samsung AI Center), Aleksei Ivakhnenko (Samsung AI Center), Yury Malkov (Samsung AI Center), Igor Pasechnik (Samsung AI Center), Dmitry Ulyanov (Samsung AI Center, Skolkovo Institute of Science and Technology), Alexander Vakhitov (Samsung AI Center, Skolkovo Institute of Science and Technology), Victor Lempitsky (Samsung AI Center, Skolkovo Institute of Science and Technology)

499Self-Supervised Adaptation of High-Fidelity Face Models for Monocular Performance Tracking



WednesdayOral 2.1C8:48WednesdayPoster 2.1138Jae Shin Yoon

501IM-Net for High Resolution Video Frame Interpolation



TuesdayOral 1.2B14:16TuesdayPoster 1.2126Tomer Peleg

503Towards Social Artificial Intelligence: Nonverbal Social Signal Prediction in a Triadic Interaction



ThursdayOral 3.2B14:11ThursdayPoster 3.299Hanbyul Joo

505Cycle-Consistency for Robust Visual Question Answering



WednesdayOral 2.2B14:11WednesdayPoster 2.2184Meet Shah

506Efficient Video Classification Using Fewer Frames



TuesdayOral 1.1C10:04TuesdayPoster 1.1120Shweta Bhardwaj

507Diverse Generation for Multi-Agent Sports Games



WednesdayOral 2.1C8:53WednesdayPoster 2.1139Raymond A. Yeh

508Relational Action Forecasting



TuesdayOral 1.1C9:18TuesdayPoster 1.1112Chen Sun

509Barrage of Random Transforms for Adversarially Robust Defense



WednesdayOral 2.2A14:47WednesdayPoster 2.238Edward Raff

511Unified Visual-Semantic Embeddings: Bridging Vision and Language With Structured Meaning Representations



WednesdayOral 2.2B13:48WednesdayPoster 2.2180Hao Wu

514GFrames: Gradient-Based Local Reference Frame for 3D Shape Matching



WednesdayOral 2.1C9:06WednesdayPoster 2.1141Simone Melzi

515Learning Structure-And-Motion-Aware Rolling Shutter Correction



WednesdayOral 2.1B9:47WednesdayPoster 2.1119Bingbing Zhuang

516Do Better ImageNet Models Transfer Better?



TuesdayOral 1.2C15:10TuesdayPoster 1.2183Simon Kornblith

518Streamlined Dense Video Captioning



WednesdayOral 2.2B13:35WednesdayPoster 2.2178Jonghwan Mun

520Enhancing Diversity of Defocus Blur Detectors via Cross-Ensemble Network



ThursdayOral 3.1C9:24ThursdayPoster 3.164Wenda Zhao

521Neural Illumination: Lighting Prediction for Indoor Environments



WednesdayOral 2.2C15:05WednesdayPoster 2.2146Shuran Song

522Shapes and Context: In-The-Wild Image Synthesis & Manipulation



TuesdayOral 1.2B13:30TuesdayPoster 1.2118Aayush Bansal

523Fast, Diverse and Accurate Image Captioning Guided by Part-Of-Speech



ThursdayOral 3.2A14:11ThursdayPoster 3.28Aditya Deshpande

524Divergence Triangle for Joint Training of Generator Model, Energy-Based Model, and Inferential Model



ThursdayOral 3.1B8:30ThursdayPoster 3.177Tian Han

525Learning to Synthesize Motion Blur

http://timothybrooks.com/tech/motion-blur/
WednesdayOral 2.2C14:16WednesdayPoster 2.2138Tim BrooksTim Brooks, Jonathan T. Barron

527Defense Against Adversarial Images Using Web-Scale Nearest-Neighbor Search



ThursdayOral 3.1B9:29ThursdayPoster 3.187Abhimanyu Dubey

528Gaussian Temporal Awareness Networks for Action Localization



TuesdayOral 1.1C9:59TuesdayPoster 1.1119Fuchen Long

529Photon-Flooded Single-Photon 3D Cameras



WednesdayOral 2.2C13:30WednesdayPoster 2.2130Anant Gupta

530NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences



TuesdayOral 1.1B9:54TuesdayPoster 1.181Chen Zhao

531End-To-End Interpretable Neural Motion Planner



ThursdayOral 3.1A9:52ThursdayPoster 3.1204Wenyuan Zeng

532Learning Spatial Common Sense With Geometry-Aware Recurrent Networks



TuesdayOral 1.2C14:29TuesdayPoster 1.2176Hsiao-Yu Fish Tung

533Deep Reinforcement Learning of Volume-Guided Progressive View Inpainting for 3D Point Scene Completion From a Single Depth Image



TuesdayOral 1.1B10:04TuesdayPoster 1.183Xiaoguang Han

534H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions



WednesdayOral 2.1B9:24WednesdayPoster 2.1115Bugra Tekin

535d-SNE: Domain Adaptation Using Stochastic Neighborhood Embedding



TuesdayOral 1.2C13:30TuesdayPoster 1.2166Xiang Xu

536A Sufficient Condition for Convergences of Adam and RMSProp



ThursdayOral 3.2C14:52ThursdayPoster 3.2161Fangyu Zou

537Gait Recognition via Disentangled Representation Learning



WednesdayOral 2.1C9:52WednesdayPoster 2.1149Ziyuan Zhang

538Constrained Generative Adversarial Networks for Interactive Image Generation



ThursdayOral 3.2A14:47ThursdayPoster 3.214Eric Heim

539Unprocessing Images for Learned Raw Denoising

http://timothybrooks.com/tech/unprocessing/
ThursdayOral 3.2C13:58ThursdayPoster 3.2152Tim BrooksTim Brooks, Ben Mildenhall, Tianfan Xue, Jiawen Chen, Dillon Sharlet, Jonathan T. Barron

540Efficient Online Multi-Person 2D Pose Tracking With Recurrent Spatio-Temporal Affinity Fields



WednesdayOral 2.1C8:58WednesdayPoster 2.1140Yaadhav Raaj

541Cross-Modality Personalization for Retrieval



WednesdayOral 2.2A13:48WednesdayPoster 2.228Nils Murrugarra-Llerena

542FML: Face Model Learning From Videos
https://mp.weixin.qq.com/s/wxZXVtzgxzBKqWOyt9Godwhttp://gvv.mpi-inf.mpg.de/projects/FML19/
ThursdayOral 3.2B13:35ThursdayPoster 3.293Ayush TewariA. Tewari F. Bernard P. Garrido G. Bharaj M. Elgharib H-P. Seidel P. Perez M. Zollh?fer C.Theobalt

543Learning Joint Gait Representation via Quintuplet Loss Minimization



WednesdayOral 2.1C9:47WednesdayPoster 2.1148Kaihao Zhang

544Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation



ThursdayOral 3.2B14:24ThursdayPoster 3.2101Xipeng Chen

545DeepVoxels: Learning Persistent 3D Feature Embeddings



TuesdayOral 1.2B14:42TuesdayPoster 1.2130Vincent Sitzmann

546Mutual Learning of Complementary Networks via Residual Correction for Improving Semi-Supervised Classification



WednesdayOral 2.2A14:29WednesdayPoster 2.235Si Wu

547Causes and Corrections for Bimodal Multi-Path Scanning With Structured Light



WednesdayOral 2.1B8:35WednesdayPoster 2.1107Yu Zhang

548Neural RGB(r)D Sensing: Depth and Uncertainty From a Video Camera



ThursdayOral 3.2C13:30ThursdayPoster 3.2147Chao Liu

549Towards Scene Understanding: Unsupervised Monocular Depth Estimation With Semantic-Aware Representation



TuesdayOral 1.2C14:47TuesdayPoster 1.2179Po-Yi Chen

550Slim DensePose: Thrifty Learning From Sparse Annotations and Motion Cues



ThursdayOral 3.2B14:34ThursdayPoster 3.2103Natalia Neverova

551Inverse Procedural Modeling of Knitwear



ThursdayOral 3.1A9:34ThursdayPoster 3.1201Elena Trunz

552Online High Rank Matrix Completion



ThursdayOral 3.1B8:40ThursdayPoster 3.179Jicong Fan

553Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation
https://mp.weixin.qq.com/s/LsHWkdwqqrOPFgCNNcBdpg

WednesdayOral 2.2B13:58WednesdayPoster 2.2182Xin WangXin Wang, Qiuyuan Huang, Asli Celikyilmaz, Jianfeng Gao, Dinghan Shen, Yuan-Fang Wang, William Yang Wang, Lei Zhang

554SDC - Stacked Dilated Convolution: A Unified Descriptor Network for Dense Matching Tasks



TuesdayOral 1.2C14:06TuesdayPoster 1.2172Rene Schuster

555Guaranteed Matrix Completion Under Multiple Linear Transformations



ThursdayOral 3.2C15:00ThursdayPoster 3.2162Chao Li

556AutoAugment: Learning Augmentation Strategies From Data



TuesdayOral 1.1A10:04TuesdayPoster 1.112Ekin D. Cubuk

557DeepView: View Synthesis With Learned Gradient Descent



TuesdayOral 1.2B13:58TuesdayPoster 1.2123John Flynn

558C2AE: Class Conditioned Auto-Encoder for Open-Set Recognition



TuesdayOral 1.2A15:10TuesdayPoster 1.235Poojan Oza

559Reasoning-RCNN: Unifying Adaptive Global Reasoning Into Large-Scale Object Detection



WednesdayOral 2.2A13:40WednesdayPoster 2.227Hang Xu

560A Theory of Fermat Paths for Non-Line-Of-Sight Shape Reconstruction



WednesdayOral 2.2C13:53WednesdayPoster 2.2134Shumian Xin

561Combining 3D Morphable Models: A Large Scale Face-And-Head Model



ThursdayOral 3.2B14:47ThursdayPoster 3.2105Stylianos Ploumpis

562Lifting Vectorial Variational Problems: A Natural Formulation Based on Geometric Measure Theory and Discrete Exterior Calculus



ThursdayOral 3.2C14:47ThursdayPoster 3.2160Thomas Mollenhoff

564Deep Sky Modeling for Single Image Outdoor Lighting Estimation



WednesdayOral 2.2C15:10WednesdayPoster 2.2147Yannick Hold-Geoffroy

565Transferrable Prototypical Networks for Unsupervised Domain Adaptation



TuesdayOral 1.2A14:29TuesdayPoster 1.228Yingwei Pan

566Learning the Depths of Moving People by Watching Frozen People



WednesdayOral 2.1B9:29WednesdayPoster 2.1116Zhengqi Li

567Blending-Target Domain Adaptation by Adversarial Meta-Adaptation Networks



TuesdayOral 1.2A14:34TuesdayPoster 1.229Ziliang Chen

568Semantic Correlation Promoted Shape-Variant Context for Segmentation



ThursdayOral 3.1C9:11ThursdayPoster 3.162Henghui Ding

569Pushing the Boundaries of View Extrapolation With Multiplane Images



TuesdayOral 1.1B9:28TuesdayPoster 1.177Pratul P. Srinivasan

572Holistic and Comprehensive Annotation of Clinically Significant Findings on Diverse CT Images: Learning From Radiology Reports and Label Ontology



ThursdayOral 3.1A8:30ThursdayPoster 3.1190Ke Yan

573Point in, Box Out: Beyond Counting Persons in Crowds



WednesdayOral 2.2A14:11WednesdayPoster 2.232Yuting Liu

574Striking the Right Balance With Uncertainty



TuesdayOral 1.1A9:59TuesdayPoster 1.111Salman Khan

575Strand-Accurate Multi-View Hair Capture



TuesdayOral 1.1B9:18TuesdayPoster 1.175Giljoo Nam

576In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations



ThursdayOral 3.2B14:29ThursdayPoster 3.2102Ikhsanul Habibie

577Blind Visual Motif Removal From a Single Image



WednesdayOral 2.2C14:29WednesdayPoster 2.2140Amir Hertz

579Boosting Local Shape Matching for Dense 3D Face Correspondence



ThursdayOral 3.2B14:52ThursdayPoster 3.2106Zhenfeng Fan

580A Convex Relaxation for Multi-Graph Matching



ThursdayOral 3.2C15:10ThursdayPoster 3.2164Paul Swoboda

581Learning Correspondence From the Cycle-Consistency of Time

https://ajabri.github.io/timecycle/
TuesdayOral 1.2C14:11TuesdayPoster 1.2173Xiaolong WangXiaolong Wang, Allan Jabri, Alexei A. Efros

582Which Way Are You Going? Imitative Decision Learning for Path Forecasting in Dynamic Scenes



TuesdayOral 1.1C9:28TuesdayPoster 1.1114Yuke Li

583What Correspondences Reveal About Unknown Camera and Motion Models?



ThursdayOral 3.1B9:06ThursdayPoster 3.183Thomas Probst

584Long-Term Feature Banks for Detailed Video Understanding



TuesdayOral 1.1C9:23TuesdayPoster 1.1113Chao-Yuan Wu

586GeoNet: Deep Geodesic Networks for Point Cloud Analysis
https://mp.weixin.qq.com/s/2dqw6__2k51B4SSkLYRTfw?

WednesdayOral 2.2C14:47WednesdayPoster 2.2143Tong HeTong He, Haibin Huang, Li Yi, Yuqian Zhou, Chihao Wu, Jue Wang, Stefano Soatto

587Coordinate-Free Carlsson-Weinshall Duality and Relative Multi-View Geometry



TuesdayOral 1.1B9:59TuesdayPoster 1.182Matthew Trager

588Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks



WednesdayOral 2.1A8:53WednesdayPoster 2.15Yinpeng Dong

589Robust Subspace Clustering With Independent and Piecewise Identically Distributed Noise Modeling



ThursdayOral 3.1B8:58ThursdayPoster 3.182Yuanman Li

590HoloPose: Holistic 3D Human Reconstruction In-The-Wild



ThursdayOral 3.2B14:16ThursdayPoster 3.2100Riza Alp Guler

591CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
https://mp.weixin.qq.com/s/68OW_7EIkzCF4HnBVcz6qg

ThursdayOral 3.1B9:47ThursdayPoster 3.190Zheng TangZheng Tang, Milind Naphade, Ming-Yu Liu, Xiaodong Yang, Stan Birchfield, Shuo Wang, Ratnesh Kumar, David Anastasiu, Jenq-Neng Hwang

592Neural Task Graphs: Generalizing to Unseen Tasks From a Single Video Demonstration



ThursdayOral 3.1A8:53ThursdayPoster 3.1194De-An Huang

593On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions



TuesdayOral 1.1A9:28TuesdayPoster 1.16Yusuke Tsuzuku

595Eliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking



WednesdayOral 2.1C9:11WednesdayPoster 2.1142Andrii Maksai

596Balanced Self-Paced Learning for Generative Adversarial Clustering Network



WednesdayOral 2.1A9:42WednesdayPoster 2.113Kamran Ghasedi

597LAF-Net: Locally Adaptive Fusion Networks for Stereo Confidence Estimation



TuesdayOral 1.1B9:46TuesdayPoster 1.180Sunok Kim

598AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations



ThursdayOral 3.2B13:40ThursdayPoster 3.294Xiao Zhang

599Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection



WednesdayOral 2.1A9:24WednesdayPoster 2.110Ruoqi Sun

600STEP: Spatio-Temporal Progressive Learning for Video Action Detection



TuesdayOral 1.1C9:10TuesdayPoster 1.1111Xitong Yang

601Tangent-Normal Adversarial Regularization for Semi-Supervised Learning



ThursdayOral 3.2A13:58ThursdayPoster 3.26Bing Yu

602Underexposed Photo Enhancement Using Deep Illumination Estimation



WednesdayOral 2.2C14:24WednesdayPoster 2.2139Ruixing Wang

603Deep Tree Learning for Zero-Shot Face Anti-Spoofing



WednesdayOral 2.1C9:34WednesdayPoster 2.1146Yaojie Liu

604Multimodal Explanations by Predicting Counterfactuality in Videos



ThursdayOral 3.1A9:11ThursdayPoster 3.1197Atsushi Kanehira

605The Visual Centrifuge: Model-Free Layered Video Representations



TuesdayOral 1.2B14:52TuesdayPoster 1.2132Jean-Baptiste Alayrac

606AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs



WednesdayOral 2.2A15:10WednesdayPoster 2.242Massimiliano Mancini

607MeshAdv: Adversarial Meshes for Visual Recognition



WednesdayOral 2.2C14:52WednesdayPoster 2.2144Chaowei Xiao

608Incremental Object Learning From Contiguous Views



ThursdayOral 3.1B9:34ThursdayPoster 3.188Stefan Stojanov

609Mitigating Information Leakage in Image Representations: A Maximum Entropy Approach



TuesdayOral 1.2C14:24TuesdayPoster 1.2175Proteek Chandan Roy

610Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss



WednesdayOral 2.1A9:16WednesdayPoster 2.19Sangil Jung

611Estimating 3D Motion and Forces of Person-Object Interactions From Monocular Video



ThursdayOral 3.1A9:42ThursdayPoster 3.1202Zongmian Li

612Robust Histopathology Image Analysis: To Label or to Synthesize?



ThursdayOral 3.1A8:35ThursdayPoster 3.1191Le Hou

613BAD SLAM: Bundle Adjusted Direct RGB-D SLAM



TuesdayOral 1.1B9:05TuesdayPoster 1.173Thomas Schops

614Learning Personalized Modular Network Guided by Structured Knowledge



ThursdayOral 3.1C9:47ThursdayPoster 3.168Xiaodan Liang

615Embodied Question Answering in Photorealistic Environments With Point Cloud Perception



WednesdayOral 2.2B14:16WednesdayPoster 2.2185Erik Wijmans

616What and How Well You Performed? A Multitask Learning Approach to Action Quality Assessmen



TuesdayOral 1.1C9:36TuesdayPoster 1.1115Paritosh Parmar

618ContextDesc: Local Descriptor Augmentation With Cross-Modality Context



TuesdayOral 1.2C13:48TuesdayPoster 1.2169Zixin Luo

619Adaptive NMS: Refining Pedestrian Detection in a Crowd



WednesdayOral 2.2A14:06WednesdayPoster 2.231Songtao Liu

620Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth



ThursdayOral 3.1C8:40ThursdayPoster 3.157Davy Neven

621Inverse Path Tracing for Joint Material and Lighting Estimation



TuesdayOral 1.2B14:47TuesdayPoster 1.2131Dejan Azinovic

622Adversarial Attacks Beyond the Image Space



WednesdayOral 2.1A8:48WednesdayPoster 2.14Xiaohui Zeng

623Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning Model



TuesdayOral 1.1C9:54TuesdayPoster 1.1118Weining Wang

624High-Quality Face Capture Using Anatomical Muscles



ThursdayOral 3.2B13:30ThursdayPoster 3.292Michael Bao

625APDrawingGAN: Generating Artistic Portrait Drawings From Face Photos With Hierarchical GANs



ThursdayOral 3.2A14:42ThursdayPoster 3.213Ran Yi

626GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering



WednesdayOral 2.2B14:42WednesdayPoster 2.2189Drew A. Hudson

627Panoptic Feature Pyramid Networks



WednesdayOral 2.2A13:30WednesdayPoster 2.225Alexander Kirillov

628Image Deformation Meta-Networks for One-Shot Learning



ThursdayOral 3.1B8:35ThursdayPoster 3.178Zitian Chen

629Learning Loss for Active Learning



TuesdayOral 1.1A9:54TuesdayPoster 1.110Donggeun Yoo

630Graph Convolutional Tracking



WednesdayOral 2.1C9:16WednesdayPoster 2.1143Junyu Gao

631Tell Me Where I Am: Object-Level Scene Context Prediction



TuesdayOral 1.2C14:52TuesdayPoster 1.2180Xiaotian Qiao

632Max-Sliced Wasserstein Distance and Its Use for GANs



ThursdayOral 3.2A13:40ThursdayPoster 3.23Ishan Deshpande

633Composing Text and Image for Image Retrieval - an Empirical Odyssey



WednesdayOral 2.2A13:53WednesdayPoster 2.229Nam Vo

634Residual Networks for Light Field Image Super-Resolution



ThursdayOral 3.2C14:06ThursdayPoster 3.2153Shuo Zhang

635Explainability Methods for Graph Convolutional Neural Networks



ThursdayOral 3.2A15:00ThursdayPoster 3.216Phillip E. Pope

637SoDeep: A Sorting Deep Net to Learn Ranking Loss Surrogates



ThursdayOral 3.2A15:10ThursdayPoster 3.218Martin Engilberge

638"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors



ThursdayOral 3.2C13:53ThursdayPoster 3.2151Yosef Gandelsman

639Doodle to Search: Practical Zero-Shot Sketch-Based Image Retrieval



TuesdayOral 1.2A13:53TuesdayPoster 1.222Sounak Dey

640Cascaded Projection: End-To-End Network Compression and Acceleration



ThursdayOral 3.2A14:24ThursdayPoster 3.210Breton Minnehan

641High Flux Passive Imaging With Single-Photon Sensors



WednesdayOral 2.2C13:35WednesdayPoster 2.2131Atul Ingle

642A Generative Adversarial Density Estimator



ThursdayOral 3.2A15:05ThursdayPoster 3.217M. Ehsan Abbasnejad

643Sampling Techniques for Large-Scale Object Detection From Sparsely Annotated Objects



WednesdayOral 2.2A14:34WednesdayPoster 2.236Yusuke Niitani

644Non-Local Meets Global: An Integrated Paradigm for Hyperspectral Denoising



WednesdayOral 2.2C14:34WednesdayPoster 2.2141Wei He

645Dynamic Fusion With Intra- and Inter-Modality Attention Flow for Visual Question Answering



WednesdayOral 2.2B14:06WednesdayPoster 2.2183Peng Gao

646Unsupervised Part-Based Disentangling of Object Shape and Appearance



ThursdayOral 3.2B15:00ThursdayPoster 3.2107Dominik Lorenz

647Arbitrary Shape Scene Text Detection With Adaptive Text Region Representation



WednesdayOral 2.2A13:58WednesdayPoster 2.230Xiaobing Wang

648CollaGAN: Collaborative GAN for Missing Image Data Imputation



TuesdayOral 1.2B15:10TuesdayPoster 1.2135Dongwook Lee

649Semantics Disentangling for Text-To-Image Generation



TuesdayOral 1.2B13:35TuesdayPoster 1.2119Guojun Yin

650Two Body Problem: Collaborative Visual Task Completion
https://prior.allenai.org/projects/two-body-problem

WednesdayOral 2.2B14:34WednesdayPoster 2.2188Unnat JainUnnat Jain, Luca Weihs, Eric Kolve, Mohammad Rastegari, Svetlana Lazebnik, Ali Farhadi, Alexander Schwing, Aniruddha Kembhavi

6513D Shape Reconstruction From Images in the Frequency Domain



WednesdayOral 2.1B8:58WednesdayPoster 2.1111Weichao Shen

652Fast Spatially-Varying Indoor Lighting Estimation



WednesdayOral 2.2C15:00WednesdayPoster 2.2145Mathieu Garon

653Steady-State Non-Line-Of-Sight Imaging



WednesdayOral 2.2C13:48WednesdayPoster 2.2133Wenzheng Chen

654SFNet: Learning Object-Aware Semantic Correspondence



TuesdayOral 1.2A14:52TuesdayPoster 1.232Junghyup Lee

655Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping



TuesdayOral 1.2B14:34TuesdayPoster 1.2129Huan Fu

656Gradient Matching Generative Networks for Zero-Shot Learning



TuesdayOral 1.2A13:48TuesdayPoster 1.221Mert Bulent Sariyildiz

657Finding Task-Relevant Features for Few-Shot Learning by Category Traversal



TuesdayOral 1.1A9:00TuesdayPoster 1.11Hongyang Li

658Look Back and Predict Forward in Image Captioning






WednesdayPoster 2.2201Yu Qin

659Assisted Excitation of Activations: A Learning Technique to Improve Object Detectors






ThursdayPoster 3.126Mohammad Mahdi Derakhshani

660Group Sampling for Scale Invariant Face Detection






TuesdayPoster 1.297Xiang Ming

661Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNN






TuesdayPoster 1.189Shiyi Lan

662Domain-Specific Batch Normalization for Unsupervised Domain Adaptation






WednesdayPoster 2.262Woong-Gi Chang

663Radial Distortion Triangulation






ThursdayPoster 3.1105Zuzana Kukelova

664Polarimetric Camera Calibration Using an LCD Monitor






TuesdayPoster 1.2145Zhixiang Wang

665Towards High-Fidelity Nonlinear 3D Face Morphable Model

http://cvlab.cse.msu.edu/project-nonlinear-3dmm.html?



TuesdayPoster 1.1102Luan TranLuan Tran, Feng Liu, Xiaoming Liu

666Towards Instance-Level Image-To-Image Translation






TuesdayPoster 1.2139Zhiqiang Shen

667Structure-Preserving Stereoscopic View Synthesis With Multi-Scale Adversarial Correlation Matching






WednesdayPoster 2.1162Yu Zhang

668Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks






WednesdayPoster 2.259N. Dinesh Reddy

669Co-Occurrence Neural Network






WednesdayPoster 2.124Irina Shevlev

670Learning to Film From Professional Human Motion Videos






TuesdayPoster 1.2214Chong Huang

671Stochastic Class-Based Hard Example Mining for Deep Metric Learning






WednesdayPoster 2.251Yumin Suh

672Modularized Textual Grounding for Counterfactual Resilience






WednesdayPoster 2.1215Zhiyuan Fang

673Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis






ThursdayPoster 3.2116Yu Yu

674Global Second-Order Pooling Convolutional Networks






TuesdayPoster 1.255Zilin Gao

675Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation






TuesdayPoster 1.118Bohan Zhuang

676Revisiting Perspective Information for Efficient Crowd Counting






WednesdayPoster 2.254Miaojing Shi

677Spectral Reconstruction From Dispersive Blur: A Novel Light Efficient Spectral Imager






ThursdayPoster 3.2143Yuanyuan Zhao

678Joint Face Detection and Facial Motion Retargeting for Multiple Faces






ThursdayPoster 3.1109Bindita Chaudhuri

680Perturbation Analysis of the 8-Point Algorithm: A Case Study for Wide FoV Cameras






ThursdayPoster 3.280Thiago L. T. da Silveira

681R2GAN: Cross-Modal Recipe Retrieval With Generative Adversarial Network






ThursdayPoster 3.251Bin Zhu

682Predicting Visible Image Differences Under Varying Display Brightness and Viewing Distance






WednesdayPoster 2.189Nanyang Ye

683Local Detection of Stereo Occlusion Boundaries






TuesdayPoster 1.2153Jialiang Wang

684Attribute-Driven Feature Disentangling and Temporal Aggregation for Video Person Re-Identification






WednesdayPoster 2.136Yiru Zhao

685NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection






WednesdayPoster 2.211Golnaz Ghiasi

686Local Relationship Learning With Person-Specific Shape Regularization for Facial Action Unit Detection






ThursdayPoster 3.2114Xuesong Niu

687SimulCap : Single-View Human Performance Capture With Cloth Simulation






WednesdayPoster 2.196Tao Yu

688Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture






ThursdayPoster 3.2139Ning Yu

689Convolutional Relational Machine for Group Activity Recognition






WednesdayPoster 2.2117Sina Mokhtarzadeh Azar

690Privacy Protection in Street-View Panoramas Using Depth and Multi-View Imagery






ThursdayPoster 3.1212Ries Uittenbogaard

691PMS-Net: Robust Haze Removal Based on Patch Map for Single Images






ThursdayPoster 3.272Wei-Ting Chen

692CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency






TuesdayPoster 1.1181Yun-Chun Chen

693Focus Is All You Need: Loss Functions for Event-Based Vision






ThursdayPoster 3.2169Guillermo Gallego

694TraPHic: Trajectory Prediction in Dense and Heterogeneous Traffic Using Weighted Interactions






WednesdayPoster 2.2213Rohan Chandra

695Neighbourhood Watch: Referring Expression Comprehension via Language-Guided Graph Attention Networks






TuesdayPoster 1.1198Peng Wang

697Grounding Human-To-Vehicle Advice for Self-Driving Vehicles






ThursdayPoster 3.1213Jinkyu Kim

698Divergence Prior and Vessel-Tree Reconstruction






ThursdayPoster 3.1160Zhongwen Zhang

699Rules of the Road: Predicting Driving Behavior With a Convolutional Model of Semantic Interactions






WednesdayPoster 2.2210Joey Hong

700TraVeLGAN: Image-To-Image Translation by Transformation Vector Learning






ThursdayPoster 3.13Matthew Amodio

701IRLAS: Inverse Reinforcement Learning for Architecture Search






ThursdayPoster 3.17Minghao Guo

702Scene Categorization From Contours: Medial Axis Based Salience Measures






TuesdayPoster 1.2201Morteza Rezanejad

703Single Image Depth Estimation Trained via Depth From Defocus Cues






WednesdayPoster 2.296Shir Gur

704MBS: Macroblock Scaling for CNN Model Reduction






ThursdayPoster 3.117Yu-Hsun Lin

705Deep Asymmetric Metric Learning via Rich Relationship Mining






TuesdayPoster 1.2197Xinyi Xu

707Engaging Image Captioning via Personality






ThursdayPoster 3.2193Kurt Shuster

708Quasi-Unsupervised Color Constancy






ThursdayPoster 3.2144Simone Bianco

709Typography With Decor: Intelligent Text Style Transfer






WednesdayPoster 2.1165Wenjing Wang

710Convolutional Neural Networks Can Be Deceived by Visual Illusions






ThursdayPoster 3.2172Alexander Gomez-Villa

711Label Propagation for Deep Semi-Supervised Learning






WednesdayPoster 2.152Ahmet Iscen

712Recurrent Neural Networks With Intra-Frame Iterations for Video Deblurring






WednesdayPoster 2.2156Seungjun Nah

713Deep Flow-Guided Video Inpainting






TuesdayPoster 1.2143Rui Xu

714End-To-End Time-Lapse Video Synthesis From a Single Outdoor Image






TuesdayPoster 1.1142Seonghyeon Nam

715Face Parsing With RoI Tanh-Warping






WednesdayPoster 2.1126Jinpeng Lin

716Dichromatic Model Based Temporal Color Constancy for AC Light Sources






ThursdayPoster 3.2174Jun-Sang Yoo

717Snapshot Distillation: Teacher-Student Optimization in One Generation






TuesdayPoster 1.238Chenglin Yang

718Large Scale Incremental Learning






TuesdayPoster 1.114Yue Wu

719Variational Autoencoders Pursue PCA Directions (by Accident)






ThursdayPoster 3.2182Michal Rolinek

720SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360deg Images






ThursdayPoster 3.124Yeonkun Lee

721Learning With Batch-Wise Optimal Transport Loss for 3D Shape Recognition






TuesdayPoster 1.286Lin Xu

722EV-Gait: Event-Based Robust Gait Recognition Using Dynamic Vision Sensors






WednesdayPoster 2.1213Yanxiang Wang

723Reducing Uncertainty in Undersampled MRI Reconstruction With Active Acquisition






TuesdayPoster 1.1207Zizhao Zhang

724Cross-Modal Self-Attention Network for Referring Image Segmentation






ThursdayPoster 3.1189Linwei Ye

725Residual Regression With Semantic Prior for Crowd Counting






TuesdayPoster 1.2193Jia Wan

726LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving






ThursdayPoster 3.2209Gregory P. Meyer

727VITAMIN-E: VIsual Tracking and MappINg With Extremely Dense Feature Points






ThursdayPoster 3.1101Masashi Yokozuka

728Atlas of Digital Pathology: A Generalized Hierarchical Histological Tissue Type-Annotated Database for Deep Learning






ThursdayPoster 3.279Mahdi S. Hosseini

729ROI Pooled Correlation Filters for Visual Tracking






WednesdayPoster 2.1154Yuxuan Sun

730Circulant Binary Convolutional Networks: Enhancing the Performance of 1-Bit DCNNs With Circulant Back Propagation






TuesdayPoster 1.23Chunlei Liu

731Attention-Guided Unified Network for Panoptic Segmentation
https://mp.weixin.qq.com/s/1tohID6SM3weS476XU5okw?




WednesdayPoster 2.210Yanwei LiYanwei Li, Xinze Chen, Zheng Zhu, Lingxi Xie, Guan Huang, Dalong Du, Xingang Wang

732Intention Oriented Image Captions With Guiding Objects






WednesdayPoster 2.2204Yue Zheng

733Weakly Supervised Video Moment Retrieval From Text Queries






ThursdayPoster 3.263Niluthpol Chowdhury Mithun

734Effective Aesthetics Prediction With Multi-Level Spatially Pooled Features






ThursdayPoster 3.144Vlad Hosu

735AANet: Attribute Attention Network for Person Re-Identifications






WednesdayPoster 2.221Chiat-Pin Tay

736Feature-Level Frankenstein: Eliminating Variations for Discriminative Recognition






TuesdayPoster 1.141Xiaofeng Liu

737Interaction-And-Aggregation Network for Person Re-Identification






ThursdayPoster 3.138Ruibing Hou

738Veritatem Dies Aperit - Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach






TuesdayPoster 1.290Amir Atapour-Abarghouei

739Photo Wake-Up: 3D Character Animation From a Single Photo






WednesdayPoster 2.1167Chung-Yi Weng

740Adversarial Defense by Stratified Convolutional Sparse Coding






ThursdayPoster 3.248Bo Sun

741Customizable Architecture Search for Semantic Segmentation






ThursdayPoster 3.268Yiheng Zhang

742Neuro-Inspired Eye Tracking With Eye Movement Dynamics






ThursdayPoster 3.1120Kang Wang

743On Learning Density Aware Embeddings






WednesdayPoster 2.133Soumyadeep Ghosh

744Accelerating Convolutional Neural Networks via Activation Map Compression






WednesdayPoster 2.216Georgios Georgiadis

745Characterizing and Avoiding Negative Transfer






ThursdayPoster 3.232Zirui Wang

746Weakly Supervised Image Classification Through Noise Regularization






ThursdayPoster 3.255Mengying Hu

748You Reap What You Sow: Using Videos to Generate High Precision Object Proposals for Weakly-Supervised Object Detection






ThursdayPoster 3.148Krishna Kumar Singh

749On Implicit Filter Level Sparsity in Convolutional Neural Networks






TuesdayPoster 1.129Dushyant Mehta

750T-Net: Parametrizing Fully Convolutional Nets With a Single High-Order Tensor






WednesdayPoster 2.2110Jean Kossaifi

751Learning Binary Code for Personalized Fashion Recommendation






ThursdayPoster 3.1210Zhi Lu

752Hyperspectral Image Super-Resolution With Optimized RGB Guidance






ThursdayPoster 3.270Ying Fu

753Learning Active Contour Models for Medical Image Segmentation






ThursdayPoster 3.267Xu Chen

754Graph Attention Convolution for Point Cloud Semantic Segmentation






ThursdayPoster 3.1168Lei Wang

755Coordinate-Based Texture Inpainting for Pose-Guided Human Image Generation






ThursdayPoster 3.2136Artur Grigorev

756Detection Based Defense Against Adversarial Examples From the Steganalysis Point of View






WednesdayPoster 2.127Jiayang Liu

757A Parametric Top-View Representation of Complex Road Scenes






ThursdayPoster 3.1171Ziyan Wang

758Unsupervised Learning of Consensus Maximization for 3D Vision Problems






TuesdayPoster 1.170Thomas Probst

759LVIS: A Dataset for Large Vocabulary Instance Segmentation






WednesdayPoster 2.181Agrim Gupta

761Audio Visual Scene-Aware Dialog






WednesdayPoster 2.283Huda Alamri

762Graph-Based Global Reasoning Networks






TuesdayPoster 1.120Yunpeng Chen

763Adversarial Structure Matching for Structured Prediction Tasks






TuesdayPoster 1.2195Jyh-Jing Hwang

764Face Anti-Spoofing: Model Matters, so Does Data






TuesdayPoster 1.2103Xiao Yang

765Unsupervised Domain-Specific Deblurring via Disentangled Representations






ThursdayPoster 3.1161Boyu Lu

766Propagation Mechanism for Deep and Wide Neural Networks






ThursdayPoster 3.128Dejiang Xu

767MirrorGAN: Learning Text-To-Image Generation by Redescription






TuesdayPoster 1.1152Tingting QiaoTingting Qiao, Jing Zhang, Duanqing Xu, Dacheng Tao

768What's to Know? Uncertainty as a Guide to Asking Goal-Oriented Questions






TuesdayPoster 1.2205Ehsan Abbasnejad

769Pushing the Envelope for RGB-Based Dense 3D Hand Pose Estimation via Neural Rendering






TuesdayPoster 1.196Seungryul Baek

770Improving Referring Expression Grounding With Cross-Modal Attention-Guided Erasing






TuesdayPoster 1.1197Xihui Liu

771ShieldNets: Defending Against Adversarial Attacks Using Probabilistic Adversarial Robustness






WednesdayPoster 2.26Rajkumar Theagarajan

772Semi-Supervised Transfer Learning for Image Rain Removal






TuesdayPoster 1.2159Wei Wei

773Assessing Personally Perceived Image Quality via Image Features and Collaborative Filtering






WednesdayPoster 2.2163Jari Korhonen

774Layout-Graph Reasoning for Fashion Landmark Detection






TuesdayPoster 1.246Weijiang Yu

775RES-PCA: A Scalable Approach to Recovering Low-Rank Matrices






WednesdayPoster 2.258Chong Peng

776Using Unknown Occluders to Recover Hidden Scenes






ThursdayPoster 3.2146Adam B. Yedidia

778Turn a Silicon Camera Into an InGaAs Camera






WednesdayPoster 2.1175Feifan Lv

779Object Detection With Location-Aware Deformable Convolution and Backward Attention Filtering






ThursdayPoster 3.152Chen Zhang

780D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation






TuesdayPoster 1.2107Chien-Yi Chang

781Learning Channel-Wise Interactions for Binary Convolutional Neural Networks






TuesdayPoster 1.134Ziwei Wang

782Deep Multimodal Clustering for Unsupervised Audiovisual Learning






ThursdayPoster 3.131Di Hu

783Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting






ThursdayPoster 3.2215Muming Zhao

784AdaFrame: Adaptive Frame Selection for Fast Video Recognition






TuesdayPoster 1.1129Zuxuan Wu

785World From Blur






WednesdayPoster 2.2214Jiayan Qiu

786EventNet: Asynchronous Recursive Event Processing






TuesdayPoster 1.2160Yusuke Sekikawa

787Towards Accurate One-Stage Object Detection With AP-Loss






WednesdayPoster 2.157Kean Chen

788Completeness Modeling and Context Separation for Weakly Supervised Temporal Action Localization






TuesdayPoster 1.1131Daochang Liu

789Progressive Feature Alignment for Unsupervised Domain Adaptation






TuesdayPoster 1.140Chaoqi Chen

790Domain-Symmetric Networks for Adversarial Domain Adaptation






WednesdayPoster 2.148Yabin Zhang

791Multi-Granularity Generator for Temporal Action Proposal






TuesdayPoster 1.2113Yuan Liu

792Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks






ThursdayPoster 3.115Jorg Wagner

793Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification From the Bottom Up






TuesdayPoster 1.256Weifeng Ge

794Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning






ThursdayPoster 3.250Bin Tong

795Classification-Reconstruction Learning for Open-Set Recognition






TuesdayPoster 1.2191Ryota Yoshihashi

796A Variational Pan-Sharpening With Local Gradient Constraints






ThursdayPoster 3.1165Xueyang Fu

797Non-Adversarial Image Synthesis With Generative Latent Nearest Neighbors






WednesdayPoster 2.1157Yedid Hoshen

798An End-To-End Network for Panoptic Segmentation






WednesdayPoster 2.1194Huanyu Liu

799ToothNet: Automatic Tooth Instance Segmentation and Identification From Cone Beam CT Images






WednesdayPoster 2.1214Zhiming Cui

800Unsupervised Disentangling of Appearance and Geometry by Deformable Generator Network






ThursdayPoster 3.1174Xianglei Xing

801A Variational Auto-Encoder Model for Stochastic Point Processes






TuesdayPoster 1.269Nazanin Mehrasa

802Cyclic Guidance for Weakly Supervised Joint Detection and Segmentation






TuesdayPoster 1.147Yunhang Shen

803RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection






WednesdayPoster 2.165Leonid Karlinsky

804Deep ChArUco: Dark ChArUco Marker Pose Estimation






WednesdayPoster 2.2208Danying Hu

805Learning-Based Sampling for Natural Image Matting






TuesdayPoster 1.258Jingwei Tang

806Actively Seeking and Learning From Live Data






TuesdayPoster 1.1196Damien Teney

807Depth Coefficients for Depth Completion






ThursdayPoster 3.2186Saif Imran

808PDE Acceleration for Active Contours






ThursdayPoster 3.2173Anthony Yezzi

809On the Intrinsic Dimensionality of Image Representations






TuesdayPoster 1.2188Sixue Gong

810PA3D: Pose-Action 3D Machine for Video Recognition






WednesdayPoster 2.2120An Yan

811UniformFace: Learning Deep Equidistributed Representation for Face Recognition






TuesdayPoster 1.294Yueqi Duan

812Direct Object Recognition Without Line-Of-Sight Using Optical Coherence






ThursdayPoster 3.278Xin Lei

813Deep Dual Relation Modeling for Egocentric Interaction Recognition






WednesdayPoster 2.2121Haoxin Li

814Learning Independent Object Motion From Unlabelled Stereoscopic Videos






WednesdayPoster 2.1105Zhe Cao

815Spectral Metric for Dataset Complexity Assessment






TuesdayPoster 1.274Frederic Branchaud-Charron

816Progressive Ensemble Networks for Zero-Shot Recognition






ThursdayPoster 3.277Meng Ye

818Grid R-CNN






WednesdayPoster 2.263Xin Lu

819Spatial-Aware Graph Relation Network for Large-Scale Object Detection






ThursdayPoster 3.136Hang Xu

821Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics






WednesdayPoster 2.2207Yaron Meirovitch

822ECC: Platform-Independent Energy-Constrained Deep Neural Network Compression via a Bilinear Regression Model






ThursdayPoster 3.223Haichuan Yang

823Led3D: A Lightweight and Efficient Deep Approach to Recognizing Low-Quality 3D Faces






WednesdayPoster 2.1153Guodong Mu

824MSCap: Multi-Style Image Captioning With Unpaired Stylized Text






TuesdayPoster 1.2210Longteng Guo

826DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition






WednesdayPoster 2.2113Toby Perrett

827Weakly Supervised Open-Set Domain Adaptation by Dual-Domain Collaboration






WednesdayPoster 2.185Shuhan Tan

828MARS: Motion-Augmented RGB Stream for Action Recognition






WednesdayPoster 2.2116Nieves Crasto

829Less Is More: Learning Highlight Detection From Video Duration






TuesdayPoster 1.1127Bo Xiong

8303D Motion Decomposition for RGBD Future Dynamic Scene Synthesis






WednesdayPoster 2.295Xiaojuan Qi

831Distraction-Aware Shadow Detection






WednesdayPoster 2.162Quanlong Zheng

832Unifying Heterogeneous Classifiers With Distillation






TuesdayPoster 1.270Jayakorn Vongkulbhisal

833Self-Supervised Representation Learning by Rotation Feature Decoupling






ThursdayPoster 3.1175Zeyu Feng

834Compressing Convolutional Neural Networks via Factorized Convolutional Filters






TuesdayPoster 1.2187Tuanhui Li

835Discovering Fair Representations in the Data Domain






WednesdayPoster 2.2169Novi Quadrianto

836Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation






TuesdayPoster 1.2200Zhenyu Zhang

837Speech2Face: Learning the Face Behind a Voice






WednesdayPoster 2.281Tae-Hyun Oh

838Informative Object Annotations: Tell Me Something I Don't Know






ThursdayPoster 3.2192Lior Bracha

839DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-To-Image Synthesis






WednesdayPoster 2.1156Minfeng Zhu

840Gotta Adapt 'Em All: Joint Pixel and Feature-Level Domain Adaptation for Recognition in the Wild






TuesdayPoster 1.21Luan Tran

8413D Local Features for Direct Pairwise Registration






TuesdayPoster 1.277Haowen Deng

842Unsupervised Primitive Discovery for Improved 3D Generative Modeling






ThursdayPoster 3.1111Salman H. Khan

843Learning to Minify Photometric Stereo






WednesdayPoster 2.284Junxuan Li

844Learning to Calibrate Straight Lines for Fisheye Image Rectification






TuesdayPoster 1.1166Zhucun Xue

845Multispectral and Hyperspectral Image Fusion by MS/HS Fusion Net






TuesdayPoster 1.1160Qi Xie

847Selective Sensor Fusion for Neural Visual-Inertial Odometry






ThursdayPoster 3.1208Changhao Chen

848SpotTune: Transfer Learning Through Adaptive Fine-Tuning






WednesdayPoster 2.125Yunhui Guo

849Learning a Deep ConvNet for Multi-Label Classification With Partial Labels






TuesdayPoster 1.142Thibaut Durand

850Visual Question Answering as Reading Comprehension






WednesdayPoster 2.1209Hui Li

851Densely Semantically Aligned Person Re-Identification






TuesdayPoster 1.144Zhizheng Zhang

852Distilled Person Re-Identification: Towards a More Scalable System






TuesdayPoster 1.1108Ancong Wu

853Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras






ThursdayPoster 3.1163Jacques Manderscheid

854EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching From Scratch






ThursdayPoster 3.111Jian Ren

855Weakly Supervised Person Re-Identification






TuesdayPoster 1.153Jingke Meng

856Motion Estimation of Non-Holonomic Ground Vehicles From a Single Feature Correspondence Measured Over N Views






ThursdayPoster 3.2212Kun Huang

857How to Make a Pizza: Learning a Compositional Layer-Based GAN Model






WednesdayPoster 2.2128Dim P. Papadopoulos

858Few-Shot Learning via Saliency-Guided Hallucination of Samples






TuesdayPoster 1.211Hongguang Zhang

859Triply Supervised Decoder Networks for Joint Detection and Segmentation






WednesdayPoster 2.266Jiale Cao

860OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge






TuesdayPoster 1.272Kenneth Marino

861Dynamic Recursive Neural Network






WednesdayPoster 2.160Qiushan Guo

862Fully Learnable Group Convolution for Acceleration of Deep Neural Networks






ThursdayPoster 3.110Xijun Wang

863Sea-Thru: A Method for Removing Water From Underwater Images






TuesdayPoster 1.1170Derya Akkaynak

864Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness Against Adversarial Attack






TuesdayPoster 1.136Zhezhi He

866The Domain Transform Solver






WednesdayPoster 2.1178Akash Bapat

867A Relation-Augmented Fully Convolutional Network for Semantic Segmentation in Aerial Scenes






ThursdayPoster 3.2183Lichao Mou

868Attending to Discriminative Certainty for Domain Adaptation






TuesdayPoster 1.126Vinod Kumar Kurmi

869X2CT-GAN: Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks






ThursdayPoster 3.1216Xingde Ying

870SceneCode: Monocular Dense Semantic Reconstruction Using Learned Encoded Scene Representations






ThursdayPoster 3.282Shuaifeng Zhi

871Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network Using Truncated Gaussian Approximation






ThursdayPoster 3.247Zhezhi He

872A Neural Network Based on SPD Manifold Learning for Skeleton-Based Hand Gesture Recognition






ThursdayPoster 3.2126Xuan Son Nguyen

873Hybrid Scene Compression for Visual Localization






WednesdayPoster 2.293Federico Camposeco

874Face-Focused Cross-Stream Network for Deception Detection in Videos






WednesdayPoster 2.2108Mingyu Ding

875SeerNet: Predicting Convolutional Neural Network Feature-Map Sparsity Through Low-Bit Quantization






ThursdayPoster 3.224Shijie Cao

876Coloring With Limited Data: Few-Shot Colorization via Memory Augmented Networks






ThursdayPoster 3.231Seungjoo Yoo

877Point Cloud Oversegmentation With Graph-Structured Deep Metric Learning






WednesdayPoster 2.271Loic Landrieu

878Biologically-Constrained Graphs for Global Connectomics Reconstruction






TuesdayPoster 1.1211Brian Matejek

879Learning Image and Video Compression Through Spatial-Temporal Energy Compaction






ThursdayPoster 3.1145Zhengxue Cheng

880A Variational EM Framework With Adaptive Edge Selection for Blind Motion Deblurring






ThursdayPoster 3.1155Liuge Yang

881SAIL-VOS: Semantic Amodal Instance Level Video Object Segmentation - A Synthetic Dataset and Baselines






TuesdayPoster 1.263Yuan-Ting Hu

882Skeleton-Based Action Recognition With Directed Graph Neural Networks






WednesdayPoster 2.2119Lei Shi

883SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking






TuesdayPoster 1.2117Guangting Wang

884Beyond Volumetric Albedo -- A Surface Optimization Framework for Non-Line-Of-Sight Imaging






TuesdayPoster 1.1156Chia-Yin Tsai

885What Do Single-View 3D Reconstruction Networks Learn?






TuesdayPoster 1.293Maxim Tatarchenko

886Collaborative Spatiotemporal Feature Learning for Video Action Recognition






WednesdayPoster 2.2115Chao Li

887Low-Rank Tensor Completion With a New Tensor Nuclear Norm Induced by Invertible Linear Transforms






WednesdayPoster 2.1176Canyi Lu

888Kernel Transformer Networks for Compact Spherical Convolution






ThursdayPoster 3.151Yu-Chuan Su

889Cross-Atlas Convolution for Parameterization Invariant Learning on Textured Mesh Surface






WednesdayPoster 2.1191Shiwei Li

890DeepLight: Learning Illumination for Unconstrained Mobile Mixed Reality






WednesdayPoster 2.1168Chloe LeGendre

891Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks






ThursdayPoster 3.2110Yunfan Liu

892Mapping, Localization and Path Planning for Image-Based Navigation Using Visual Features and Map






WednesdayPoster 2.265Janine Thoma

893Interactive Full Image Segmentation by Considering All Regions Jointly






ThursdayPoster 3.266Eirikur Agustsson

894A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning






ThursdayPoster 3.1179Thanh-Toan Do

895Answer Them All! Toward Universal Visual Question Answering Models






ThursdayPoster 3.1186Robik Shrestha

896Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip Connections






TuesdayPoster 1.2156Hongyun Gao

898R3 Adversarial Network for Cross Model Face Recognition






ThursdayPoster 3.1124Ken Chen

899Deep Global Generalized Gaussian Networks






WednesdayPoster 2.153Qilong Wang

900Toward Realistic Image Compositing With Adversarial Learning






WednesdayPoster 2.2206Bor-Chun Chen

901Multi-Person Pose Estimation With Enhanced Channel-Wise and Spatial Information






WednesdayPoster 2.1128Kai Su

903Exploiting Edge Features for Graph Neural Networks






ThursdayPoster 3.127Liyu Gong

904Versatile Multiple Choice Learning and Its Application to Vision Computing






WednesdayPoster 2.1212Kai Tian

905Jumping Manifolds: Geometry Aware Dense Non-Rigid Structure From Motion






WednesdayPoster 2.180Suryansh Kumar

906Semi-Supervised Learning With Graph Learning-Convolutional Networks






ThursdayPoster 3.234Bo Jiang

907Scene Graph Generation With External Knowledge and Image Reconstruction






TuesdayPoster 1.1199Jiuxiang Gu

908Large Scale High-Resolution Land Cover Mapping With Multi-Resolution Data






ThursdayPoster 3.2214Caleb Robinson

909Re-Identification With Consistent Attentive Siamese Networks






WednesdayPoster 2.1134Meng Zheng

910You Look Twice: GaterNet for Dynamic Filter Selection in CNNs






ThursdayPoster 3.123Zhourong Chen

911Understanding the Limitations of CNN-Based Absolute Camera Pose Regression






TuesdayPoster 1.283Torsten Sattler

912GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation






WednesdayPoster 2.2173Xinhong Ma

913Catastrophic Child's Play: Easy to Perform, Hard to Defend Adversarial Attacks






ThursdayPoster 3.129Chih-Hui Ho

915Recurrent Attentive Zooming for Joint Crowd Counting and Precise Localization






TuesdayPoster 1.1123Chenchen Liu

916Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition






WednesdayPoster 2.299Yinpeng Dong

918Networks for Joint Affine and Non-Parametric Image Registration






TuesdayPoster 1.2212Zhengyang Shen

919Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification






TuesdayPoster 1.151Song Bai

922Iterative Alignment Network for Continuous Sign Language Recognition






TuesdayPoster 1.2206Junfu Pu

923A Neurobiological Evaluation Metric for Neural Network Model Search






WednesdayPoster 2.186Nathaniel Blanchard

924Reflective and Fluorescent Separation Under Narrow-Band Illumination






WednesdayPoster 2.285Koji Koyamatsu

925Text Guided Person Image Synthesis






TuesdayPoster 1.2137Xingran Zhou

926An Iterative and Cooperative Top-Down and Bottom-Up Inference Network for Salient Object Detection






WednesdayPoster 2.1173Wenguan Wang

927Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs






WednesdayPoster 2.2176Qi Zhang

928Adaptive Pyramid Context Network for Semantic Segmentation






WednesdayPoster 2.279Junjun He

929Blind Geometric Distortion Correction on Images Through Deep Learning






WednesdayPoster 2.130Xiaoyu Li

930Listen to the Image






WednesdayPoster 2.2125Di Hu

931Relational Knowledge Distillation






TuesdayPoster 1.2186Wonpyo Park

932An Efficient Schmidt-EKF for 3D Visual-Inertial SLAM






ThursdayPoster 3.2133Patrick Geneva

933Pay Attention! - Robustifying a Deep Visuomotor Policy Through Task-Focused Visual Attention






TuesdayPoster 1.2215Pooya Abolghasemi

934Scalable Convolutional Neural Network for Image Compressed Sensing






ThursdayPoster 3.2170Wuzhen Shi

935TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection






ThursdayPoster 3.2121Lin Song

936Memory-Attended Recurrent Network for Video Captioning






WednesdayPoster 2.2199Wenjie Pei

937UnOS: Unified Unsupervised Optical-Flow and Stereo-Depth Estimation by Watching Videos






WednesdayPoster 2.2153Yang Wang

938Object Discovery in Videos as Foreground Motion Clustering






ThursdayPoster 3.1137Christopher Xie

939Deep Supervised Cross-Modal Retrieval






ThursdayPoster 3.1178Liangli Zhen

940Learning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification






TuesdayPoster 1.139Zhixiang Wang

941Robustness via Curvature Regularization, and Vice Versa






ThursdayPoster 3.113Seyed-Mohsen Moosavi-Dezfooli

942Feedback Adversarial Learning: Spatial Feedback for Improving Generative Adversarial Networks






TuesdayPoster 1.1149Minyoung Huh

943Learning to Explore Intrinsic Saliency for Stereoscopic Video






ThursdayPoster 3.1112Qiudan Zhang

944Ensemble Deep Manifold Similarity Learning Using Hard Proxies






WednesdayPoster 2.256Nicolas Aziere

945Hyperspectral Imaging With Random Printed Mask






ThursdayPoster 3.1153Yuanyuan Zhao

946Knowledge Distillation via Instance Relationship Graph






WednesdayPoster 2.217Yufan Liu

947Convolutional Recurrent Network for Road Boundary Extraction






ThursdayPoster 3.173Justin Liang

948ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving






WednesdayPoster 2.191Xibin Song

949LO-Net: Deep Real-Time Lidar Odometry






WednesdayPoster 2.2212Qing Li

950Building Efficient Deep Neural Networks With Unitary Group Convolutions






ThursdayPoster 3.233Ritchie Zhao

951Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes






ThursdayPoster 3.1209Chengquan Zhang

952BeautyGlow: On-Demand Makeup Transfer Framework With Reversible Generative Network






ThursdayPoster 3.1142Hung-Jen Chen

953Learning Instance Activation Maps for Weakly Supervised Instance Segmentation






TuesdayPoster 1.264Yi Zhu

954Deep Embedding Learning With Discriminative Sampling Policy






WednesdayPoster 2.141Yueqi Duan

955Events-To-Video: Bringing Modern Computer Vision to Event Cameras






TuesdayPoster 1.2157Henri Rebecq

956Improving Action Localization by Progressive Cross-Stream Cooperation






ThursdayPoster 3.2124Rui Su

958Decorrelated Adversarial Learning for Age-Invariant Face Recognition






TuesdayPoster 1.2105Hao Wang

959Neural Sequential Phrase Grounding (SeqGROUND)






TuesdayPoster 1.2207Pelin DoganPelin Dogan, Leonid Sigal, Markus Gross

961Towards Rich Feature Discovery With Class Activation Maps Augmentation for Person Re-Identification






TuesdayPoster 1.1140Wenjie Yang

962Collaborative Learning of Semi-Supervised Segmentation and Classification for Medical Images






TuesdayPoster 1.1210Yi Zhou

963Progressive Teacher-Student Learning for Early Action Prediction






TuesdayPoster 1.2108Xionghui Wang

964Unsupervised Domain Adaptation for ToF Data Denoising With Adversarial Learning






WednesdayPoster 2.1104Gianluca Agresti

965Enhanced Bayesian Compression via Deep Reinforcement Learning






WednesdayPoster 2.22Xin Yuan

966GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving






TuesdayPoster 1.191Buyu Li

967Generalizable Person Re-Identification by Domain-Invariant Mapping Network






TuesdayPoster 1.149Jifei Song

968Deep Virtual Networks for Memory Efficient Inference of Multiple Tasks






TuesdayPoster 1.25Eunwoo Kim

969Learning to Learn Relation for Important People Detection in Still Images






WednesdayPoster 2.145Wei-Hong Li

970Thinking Outside the Pool: Active Training Image Creation for Relative Attributes






TuesdayPoster 1.148Aron Yu

971Metric Learning for Image Registration






WednesdayPoster 2.2211Marc Niethammer

972Dissimilarity Coefficient Based Weakly Supervised Object Detection






ThursdayPoster 3.150Aditya Arun

973Semantic Component Decomposition for Face Attribute Manipulation






ThursdayPoster 3.1123Ying-Cong Chen

974Local to Global Learning: Gradually Adding Classes for Training Deep Neural Networks






WednesdayPoster 2.119Hao Cheng

975Combinatorial Persistency Criteria for Multicut and Max-Cut






WednesdayPoster 2.1186Jan-Hendrik Lange

976Cascaded Generative and Discriminative Learning for Microcalcification Detection in Breast Mammograms






ThursdayPoster 3.2199Fandong Zhang

977Towards Robust Curve Text Detection With Conditional Spatial Expansion






WednesdayPoster 2.253Zichuan Liu

978Geometry-Aware Distillation for Indoor Semantic Segmentation






TuesdayPoster 1.239Jianbo Jiao

980Deep Exemplar-Based Video Colorization






WednesdayPoster 2.2151Bo Zhang

981RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion






WednesdayPoster 2.297Jie Li

982Progressive Attention Memory Network for Movie Story Question Answering






WednesdayPoster 2.2198Junyeong Kim

983Semantic Attribute Matching Networks






ThursdayPoster 3.2175Seungryong Kim

984Conditional Adversarial Generative Flow for Controllable Image Synthesis






WednesdayPoster 2.2127Rui Liu

985Task Agnostic Meta-Learning for Few-Shot Learning






ThursdayPoster 3.276Muhammad Abdullah Jamal

986Deep Spectral Clustering Using Dual Autoencoder Network






TuesdayPoster 1.2196Xu Yang

988What Does It Mean to Learn in Deep Networks? And, How Does One Detect Adversarial Attacks?






WednesdayPoster 2.120Ciprian A. Corneanu

989Context-Aware Spatio-Recurrent Curvilinear Structure Segmentation






ThursdayPoster 3.2206Feigege Wang

990Local Features and Visual Words Emerge in Activations






ThursdayPoster 3.269Oriane Simeoni

991Temporal Transformer Networks: Joint Learning of Invariant and Discriminative Time Warping






ThursdayPoster 3.2184Suhas Lohit

992Zoom-In-To-Check: Boosting Video Interpolation via Instance-Level Discrimination






ThursdayPoster 3.2141Liangzhe Yuan

993Adversarial Defense Through Network Profiling Based Path Extraction






WednesdayPoster 2.122Yuxian Qiu

994Semantic Alignment: Finding Semantically Consistent Ground-Truth for Facial Landmark Detection






TuesdayPoster 1.299Zhiwei Liu

995Arbitrary Style Transfer With Style-Attentional Networks






WednesdayPoster 2.1164Dae Young Park

996Learning a Unified Classifier Incrementally via Rebalancing






TuesdayPoster 1.160Saihui Hou

997Event-Based High Dynamic Range Image and Very High Frame Rate Video Generation Using Conditional Generative Adversarial Networks






ThursdayPoster 3.1146Lin Wang

998Single Image Reflection Removal Beyond Linearity






TuesdayPoster 1.2148Qiang Wen

999Robustness Verification of Classification Deep Neural Networks via Linear Programming






ThursdayPoster 3.245Wang Lin

1000Generalising Fine-Grained Sketch-Based Image Retrieval






TuesdayPoster 1.145Kaiyue Pang

1001ChamNet: Towards Efficient Network Design Through Platform-Aware Model Adaptation






ThursdayPoster 3.243Xiaoliang Dai

1002Ray-Space Projection Model for Light Field Camera






ThursdayPoster 3.1150Qi Zhang

1003Learning to Detect Human-Object Interactions With Knowledge






TuesdayPoster 1.1204Bingjie Xu

1004End-To-End Supervised Product Quantization for Image Search and Retrieval






WednesdayPoster 2.149Benjamin Klein

1005RAVEN: A Dataset for Relational and Analogical Visual REasoNing

https://wellyzhang.github.io/project/raven.html



WednesdayPoster 2.177Chi ZhangChi Zhang, Feng Gao, Baoxiong Jia, Yixin Zhu, Song-Chun Zhu

1006Latent Filter Scaling for Multimodal Unsupervised Image-To-Image Translation






TuesdayPoster 1.1147Yazeed Alharbi

1007Efficient Featurized Image Pyramid Network for Single Shot Detector






WednesdayPoster 2.260Yanwei Pang

1008Data Representation and Learning With Graph Diffusion-Embedding Networks






ThursdayPoster 3.1180Bo Jiang

1009Enhanced Pix2pix Dehazing Network






WednesdayPoster 2.2162Yanyun Qu

1010FickleNet: Weakly and Semi-Supervised Semantic Image Segmentation Using Stochastic Inference






WednesdayPoster 2.172Jungbeom Lee

1011Adaptive Confidence Smoothing for Generalized Zero-Shot Learning






ThursdayPoster 3.271Yuval Atzmon

1012Attentive Relational Networks for Mapping Images to Scene Graphs






TuesdayPoster 1.2185Mengshi Qi

1013Multi-Task Learning of Hierarchical Vision-Language Representation






ThursdayPoster 3.1188Duy-Kien Nguyen

1014Moving Object Detection Under Discontinuous Change in Illumination Using Tensor Low-Rank and Invariant Sparse Decomposition






WednesdayPoster 2.248Moein Shakeri

1015A Content Transformation Block for Image Style Transfer






ThursdayPoster 3.1141Dmytro Kotovenko

1016Knockoff Nets: Stealing Functionality of Black-Box Models






WednesdayPoster 2.140Tribhuvanesh Orekondy

1017Unsupervised Moving Object Detection via Contextual Information Separation






TuesdayPoster 1.165Yanchao Yang

1018P2SGrad: Refined Gradients for Optimizing Deep Face Models






ThursdayPoster 3.1128Xiao Zhang

1019Fast Spatio-Temporal Residual Network for Video Super-Resolution






ThursdayPoster 3.1206Sheng Li

1020Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks






ThursdayPoster 3.2204Stephen James

1021Volumetric Capture of Humans With a Single RGBD Camera via Semi-Parametric Learning






ThursdayPoster 3.1108Rohit Pandey

1022Mind Your Neighbours: Image Annotation With Metadata Neighbourhood Graph Co-Attention Networks






TuesdayPoster 1.248Junjie Zhang

1023Modeling Point Clouds With Self-Attention and Gumbel Subset Sampling






TuesdayPoster 1.285Jiancheng YangJiancheng Yang, Qiang Zhang, Bingbing Ni, Linguo Li, Jinxian Liu, Mengdie Zhou, Qi Tian

1024Fast User-Guided Video Object Segmentation by Interaction-And-Propagation Networks






WednesdayPoster 2.170Seoung Wug Oh

1025Explicit Spatial Encoding for Deep Local Descriptors






ThursdayPoster 3.146Arun Mukundan

1026Learning Shape-Aware Embedding for Scene Text Detection






TuesdayPoster 1.2213Zhuotao Tian

1027A Structured Model for Action Detection






ThursdayPoster 3.1135Yubo Zhang

1028Scan2Mesh: From Unstructured Range Scans to 3D Meshes






WednesdayPoster 2.1103Angela Dai

1029Deep Single Image Camera Calibration With Radial Distortion






ThursdayPoster 3.286Manuel Lopez

1030Dense Classification and Implanting for Few-Shot Learning






ThursdayPoster 3.132Yann Lifchitz

1031DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color Image






TuesdayPoster 1.284Jiaxiong Qiu

1032Object Tracking by Reconstruction With View-Specific Discriminative Correlation Filters






TuesdayPoster 1.1135Ugur Kart

1033MaxpoolNMS: Getting Rid of NMS Bottlenecks in Two-Stage Object Detectors






ThursdayPoster 3.142Lile Cai

1034Visual Localization by Learning Objects-Of-Interest Dense Match Regression






WednesdayPoster 2.1124Philippe Weinzaepfel

1035Cross Domain Model Compression by Structurally Weight Sharing






ThursdayPoster 3.12Shangqian Gao

1036Learning to Generate Synthetic Data via Compositing






TuesdayPoster 1.123Shashank Tripathi

1037Fitting Multiple Heterogeneous Models by Multi-Class Cascaded T-Linkage






WednesdayPoster 2.273Luca Magri

1038Image-Question-Answer Synergistic Network for Visual Dialog






ThursdayPoster 3.1182Dalu Guo

1039Learning Multi-Class Segmentations From Single-Class Datasets






ThursdayPoster 3.172Konstantin Dmitriev

1040Phase-Only Image Based Kernel Estimation for Single Image Blind Deblurring






WednesdayPoster 2.1180Liyuan Pan

1041Feature Distillation: DNN-Oriented JPEG Compression Against Adversarial Examples






TuesdayPoster 1.163Zihao Liu

10423D Guided Fine-Grained Face Manipulation






ThursdayPoster 3.1119Zhenglin Geng

1043An End-To-End Network for Generating Social Relationship Graphs






ThursdayPoster 3.221Arushi Goel

1044Compact Feature Learning for Multi-Domain Image Classification






WednesdayPoster 2.245Yajing Liu

1045Privacy Preserving Image-Based Localization






WednesdayPoster 2.195Pablo Speciale

1046Learning View Priors for Single-View 3D Reconstruction

http://hiroharu-kato.com/projects_en/view_prior_learning.html



ThursdayPoster 3.1115Hiroharu KatoHiroharu Kato, Tatsuya Harada

1047SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraints






TuesdayPoster 1.1136Amir Sadeghian

1048Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking






WednesdayPoster 2.2123Heng Fan

1049ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis






WednesdayPoster 2.144Chao Chen

1050Automatic Face Aging in Videos via Deep Reinforcement Learning






ThursdayPoster 3.1139Chi Nhan Duong

1051Unsupervised 3D Pose Estimation With Geometric Self-Supervision






WednesdayPoster 2.1132Ching-Hang Chen

1052Did It Change? Learning to Detect Point-Of-Interest Changes for Proactive Map Updates






TuesdayPoster 1.2198Jerome Revaud

1053Blind Super-Resolution With Iterative Kernel Correction






TuesdayPoster 1.1162Jinjin Gu

1054DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep Features






TuesdayPoster 1.24Chang Tang

1055Improving the Performance of Unimodal Dynamic Hand-Gesture Recognition With Multimodal Training






TuesdayPoster 1.1106Mahdi Abavisani

1056A Late Fusion CNN for Digital Matting






WednesdayPoster 2.274Yunke Zhang

1057Double Nuclear Norm Based Low Rank Representation on Grassmann Manifolds for Clustering






ThursdayPoster 3.2130Xinglin Piao

1058Embedding Complementary Deep Networks for Image Classification






ThursdayPoster 3.130Qiuyu Chen

1060Does Learning Specific Features for Related Parts Help Human Pose Estimation?






TuesdayPoster 1.1100Wei Tang

1061Adversarial Semantic Alignment for Improved Image Captions






ThursdayPoster 3.1185Pierre Dognin

1062Learning to Learn Image Classifiers With Visual Analogy






ThursdayPoster 3.253Linjun Zhou

1063VizWiz-Priv: A Dataset for Recognizing the Presence and Purpose of Private Visual Information in Images Taken by Blind People






TuesdayPoster 1.171Danna Gurari

1064Distant Supervised Centroid Shift: A Simple and Efficient Approach to Visual Domain Adaptation






TuesdayPoster 1.250Jian Liang

1065Fully Quantized Network for Object Detection






TuesdayPoster 1.215Rundong Li

1066Learning From Noisy Labels by Regularized Estimation of Annotator Confusion






ThursdayPoster 3.227Ryutaro Tanno

1068KE-GAN: Knowledge Embedded Generative Adversarial Networks for Semi-Supervised Scene Parsing






WednesdayPoster 2.169Mengshi Qi

1069Separate to Adapt: Open Set Domain Adaptation via Progressive Separation






TuesdayPoster 1.245Hong Liu

1070Spatially Variant Linear Representation Models for Joint Filtering






TuesdayPoster 1.1172Jinshan Pan

1071Building Detail-Sensitive Semantic Segmentation Networks With Polynomial Pooling






WednesdayPoster 2.219Zhen Wei

1072Towards Universal Object Detection by Domain Attention

http://www.svcl.ucsd.edu/projects/universal-detection/?



WednesdayPoster 2.255Xudong WangXudong Wang, Zhaowei Cai, Dashan Gao, Nuno Vasconcelos

1073Salient Object Detection With Pyramid Attention and Salient Edges






TuesdayPoster 1.1146Wenguan Wang

1074Multi-Adversarial Discriminative Deep Domain Generalization for Face Presentation Attack Detection






ThursdayPoster 3.1140Rui Shao

1075CLEVR-Ref+: Diagnosing Visual Reasoning With Referring Expressions






TuesdayPoster 1.2208Runtao Liu

1076A Flexible Convolutional Solver for Fast Style Transfers






ThursdayPoster 3.11Gilles Puy

1077MVTec AD -- A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection






ThursdayPoster 3.196Paul Bergmann

1078MetaCleaner: Learning to Hallucinate Clean Representations for Noisy-Labeled Visual Recognition






WednesdayPoster 2.264Weihe Zhang

1079Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction






ThursdayPoster 3.291Jason Ku

1080Contrastive Adaptation Network for Unsupervised Domain Adaptation






WednesdayPoster 2.134Guoliang Kang

1081NetTailor: Tuning the Architecture, Not Just the Weights






TuesdayPoster 1.257Pedro Morgado

1082Variational Information Distillation for Knowledge Transfer






ThursdayPoster 3.122Sungsoo Ahn

1083FA-RPN: Floating Region Proposals for Face Detection






WednesdayPoster 2.2100Mahyar Najibi

1084Multi-Agent Tensor Fusion for Contextual Trajectory Prediction






ThursdayPoster 3.2135Tianyang Zhao

1085Bayesian Hierarchical Dynamic Model for Human Action Recognition






WednesdayPoster 2.2101Rui Zhao

1087A Decomposition Algorithm for the Sparse Generalized Eigenvalue Problem






WednesdayPoster 2.1188Ganzhao Yuan

1088Recurrent Neural Network for (Un-)Supervised Learning of Monocular Video Visual Odometry and Depth






WednesdayPoster 2.1101Rui Wang

1089F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning






ThursdayPoster 3.1166Yongqin Xian

1091Learning RoI Transformer for Oriented Object Detection in Aerial Images






TuesdayPoster 1.237Jian Ding

1092Training Deep Learning Based Image Denoisers From Undersampled Measurements Without Ground Truth and Without Image Prior






ThursdayPoster 3.1164Magauiya Zhussip

1093Action4D: Online Action Recognition in the Crowd and Clutter






ThursdayPoster 3.290Quanzeng You

1094Structural Relational Reasoning of Point Clouds






TuesdayPoster 1.184Yueqi Duan

1095Fast Object Class Labelling via Speech






WednesdayPoster 2.182Michael Gygli

1096Object Instance Annotation With Deep Extreme Level Set Evolution






WednesdayPoster 2.277Zian Wang

1097Graphical Contrastive Losses for Scene Graph Parsing






ThursdayPoster 3.257Ji Zhang

1099Time-Conditioned Action Anticipation in One Shot






ThursdayPoster 3.1130Qiuhong Ke

1100Multiview 2D/3D Rigid Registration via a Point-Of-Interest Network for Tracking and Triangulation






ThursdayPoster 3.2205Haofu Liao

1101Quantization Networks






WednesdayPoster 2.257Jiwei Yang

1102Topology Reconstruction of Tree-Like Structure in Images via Structural Similarity Measure and Dominant Set Clustering






WednesdayPoster 2.2215Jianyang Xie

1103Perceive Where to Focus: Learning Visibility-Aware Part-Level Features for Partial Person Re-Identification






TuesdayPoster 1.116Yifan Sun

1104Learning Without Memorizing






WednesdayPoster 2.159Prithviraj Dhar

1106MMFace: A Multi-Metric Regression Network for Unconstrained Face Reconstruction






WednesdayPoster 2.294Hongwei Yi

1107Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation






ThursdayPoster 3.1114Andrea Pilzer

1108Learning to Localize Through Compressed Binary Maps






ThursdayPoster 3.1170Xinkai Wei

1109Min-Max Statistical Alignment for Transfer Learning






ThursdayPoster 3.135Samitha Herath

1110Multi-Step Prediction of Occupancy Grid Maps With Recurrent Neural Networks






ThursdayPoster 3.1214Nima Mohajerin

1111Pointing Novel Objects in Image Captioning






ThursdayPoster 3.2191Yehao Li

1112Task-Free Continual Learning






ThursdayPoster 3.228Rahaf Aljundi

1113A Main/Subsidiary Network Framework for Simplifying Binary Neural Networks






WednesdayPoster 2.223Yinghao Xu

1114DMC-Net: Generating Discriminative Motion Cues for Fast Compressed Video Action Recognition






TuesdayPoster 1.1128Zheng Shou

1115Low-Rank Laplacian-Uniform Mixed Model for Robust Face Recognition






ThursdayPoster 3.2112Jiayu Dong

1116PIEs: Pose Invariant Embeddings






ThursdayPoster 3.2179Chih-Hui Ho

1117Discovering Visual Patterns in Art Collections With Spatially-Consistent Feature Learning






ThursdayPoster 3.134Xi Shen

1118Spatio-Temporal Dynamics and Semantic Attribute Enriched Visual Encoding for Video Captioning






ThursdayPoster 3.2190Nayyer Aafaq

1119Marginalized Latent Semantic Encoder for Zero-Shot Learning






WednesdayPoster 2.1196Zhengming Ding

1120Large-Scale Few-Shot Learning: Knowledge Transfer With Class Hierarchy






WednesdayPoster 2.247Aoxue Li

1121Deep Robust Subjective Visual Property Prediction in Crowdsourcing






ThursdayPoster 3.14Qianqian Xu

1122Soft Labels for Ordinal Regression






WednesdayPoster 2.118Raul Diaz

1123Learning Words by Drawing Images






TuesdayPoster 1.1205Didac Suris

1124Learning to Separate Multiple Illuminants in a Single Image






TuesdayPoster 1.2149Zhuo Hui

1125Context-Aware Visual Compatibility Prediction






ThursdayPoster 3.2203Guillem Cucurull

1126LiveSketch: Query Perturbations for Guided Sketch-Based Visual Search






TuesdayPoster 1.240John Collomosse

1127Explicit Bias Discovery in Visual Question Answering Models






ThursdayPoster 3.193Varun Manjunatha

1128Single-Frame Regularization for Temporally Stable CNNs






ThursdayPoster 3.220Gabriel Eilertsen

1129Mask-Guided Portrait Editing With Conditional GANs






TuesdayPoster 1.296Shuyang Gu

1130Large-Scale Interactive Object Segmentation With Human Annotators






ThursdayPoster 3.274Rodrigo Benenson

1131On Exploring Undetermined Relationships for Visual Relationship Detection






WednesdayPoster 2.158Yibing Zhan

1132A Compact Embedding for Facial Expression Similarity






WednesdayPoster 2.1129Raviteja Vemulapalli

1133Visual Attention Consistency Under Image Transforms for Multi-Label Image Classification






TuesdayPoster 1.150Hao Guo

1134Object-Driven Text-To-Image Synthesis via Adversarial Training






ThursdayPoster 3.2140Wenbo Li

1135Creative Flow+ Dataset






WednesdayPoster 2.184Maria Shugrina

1136Towards Real Scene Super-Resolution With Raw Images






TuesdayPoster 1.1174Xiangyu Xu

1137Inverse Discriminative Networks for Handwritten Signature Verification






WednesdayPoster 2.1152Ping Wei

1138Compressing Unknown Images With Product Quantizer for Efficient Zero-Shot Classification






WednesdayPoster 2.192Jin Li

1139Disentangling Latent Hands for Image Synthesis and Pose Estimation
https://mp.weixin.qq.com/s/U45X5kKMw_E4vfHfVmWZTA




ThursdayPoster 3.1125Linlin Yang

1140Feature Selective Anchor-Free Module for Single-Shot Object Detection






TuesdayPoster 1.161Chenchen ZhuChenchen Zhu, Yihui He, Marios Savvides

1141Rare Event Detection Using Disentangled Representation Learning






ThursdayPoster 3.139Ryuhei Hamaguchi

1142Joint Manifold Diffusion for Combining Predictions on Decoupled Observations






WednesdayPoster 2.282Kwang In Kim

1143Learning for Single-Shot Confidence Calibration in Deep Neural Networks Through Stochastic Inferences






ThursdayPoster 3.18Seonguk Seo

1144DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios






TuesdayPoster 1.167Guorun Yang

1145VRSTC: Occlusion-Free Video Person Re-Identification






WednesdayPoster 2.244Ruibing Hou

1146Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks






WednesdayPoster 2.1190Xiaolong Jiang

1147Large-Scale Weakly-Supervised Pre-Training for Video Action Recognition






ThursdayPoster 3.2127Deepti Ghadiyaram

1148Spherical Fractal Convolutional Neural Networks for Point Cloud Recognition






TuesdayPoster 1.122Yongming Rao

1149Signal-To-Noise Ratio: A Robust Distance Metric for Deep Metric Learning






WednesdayPoster 2.126Tongtong Yuan

1150All You Need Is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification






WednesdayPoster 2.250Weijie Chen

1151Deep Transfer Learning for Multiple Class Novelty Detection






ThursdayPoster 3.258Pramuditha Perera

1152Inserting Videos Into Videos






ThursdayPoster 3.1144Donghoon Lee

1153Robust Facial Landmark Detection via Occlusion-Adaptive Deep Networks






TuesdayPoster 1.2101Meilu Zhu

1154Part-Regularized Near-Duplicate Vehicle Re-Identification






TuesdayPoster 1.2189Bing He

1155Unsupervised Multi-Modal Neural Machine Translation






ThursdayPoster 3.1187Yuanhang Su

1156Video Summarization by Learning From Unpaired Data






WednesdayPoster 2.2118Mrigank Rochan

1157Putting Humans in a Scene: Learning Affordance in 3D Indoor Environments






ThursdayPoster 3.2178Xueting Li

1158Transferable AutoML by Model Sharing Over Grouped Datasets






ThursdayPoster 3.15Chao Xue

1159When Color Constancy Goes Wrong: Correcting Improperly White-Balanced Images






TuesdayPoster 1.1155Mahmoud Afifi

1160Density Map Regression Guided Detection Network for RGB-D Crowd Counting and Localization






TuesdayPoster 1.1184Dongze Lian

1161Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks






TuesdayPoster 1.131Kuan Fang

1162VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild






TuesdayPoster 1.276Yihang Lou

1163Enhancing TripleGAN for Semi-Supervised Conditional Instance Synthesis and Classification






ThursdayPoster 3.1147Si Wu

1164Knowing When to Stop: Evaluation and Verification of Conformity to Output-Size Specifications






ThursdayPoster 3.2167Chenglong Wang

1165Social Relation Recognition From Videos via Multi-Scale Spatial-Temporal Reasoning






TuesdayPoster 1.2109Xinchen Liu

1166LBS Autoencoder: Self-Supervised Fitting of Articulated Meshes to Point Clouds






ThursdayPoster 3.2119Chun-Liang Li

1167All-Weather Deep Outdoor Lighting Estimation






ThursdayPoster 3.1154Jinsong Zhang

1168Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training






WednesdayPoster 2.2216Feng Zheng

1169Not Using the Car to See the Sidewalk -- Quantifying and Controlling the Effects of Context in Classification and Segmentation






WednesdayPoster 2.2168Rakshith Shetty

1170Iterative Projection and Matching: Finding Structure-Preserving Representatives and Its Application to Computer Vision






WednesdayPoster 2.187Alireza Zaeemzadeh

1171Hyperspectral Image Reconstruction Using a Deep Spatial-Spectral Prior






WednesdayPoster 2.2149Lizhi Wang

1172Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally






ThursdayPoster 3.1121Xiuyi Jia

1173Shape Unicode: A Unified Shape Representation






TuesdayPoster 1.2150Sanjeev Muralikrishnan

1174Co-Occurrent Features in Semantic Segmentation






TuesdayPoster 1.132Hang Zhang

1175Generalized Zero-Shot Recognition Based on Visually Semantic Embedding






TuesdayPoster 1.252Pengkai Zhu

1176Foreground-Aware Image Inpainting






WednesdayPoster 2.1160Wei Xiong

1177Greedy Structure Learning of Hierarchical Compositional Models






ThursdayPoster 3.265Adam Kortylewski

1178Practical Coding Function Design for Time-Of-Flight Imaging






TuesdayPoster 1.1158Felipe Gutierrez-Barragan

1179Skin-Based Identification From Multispectral Image Data Using CNNs






ThursdayPoster 3.2176Takeshi Uemori

1180Fast and Flexible Indoor Scene Synthesis via Deep Convolutional Generative Models






WednesdayPoster 2.1195Daniel Ritchie

1181Cross-Modal Relationship Inference for Grounding Referring Expressions






TuesdayPoster 1.2204Sibei Yang

1182Polynomial Representation for Persistence Diagram






WednesdayPoster 2.1189Zhichao Wang

1183Learning Individual Styles of Conversational Gesture






TuesdayPoster 1.2102Shiry Ginosar

1184Video Magnification in the Wild Using Fractional Anisotropy in Temporal Distribution






TuesdayPoster 1.1163Shoichiro Takeda

1185Box-Driven Class-Wise Region Masking and Filling Rate Guided Loss for Weakly Supervised Semantic Segmentation






TuesdayPoster 1.266Chunfeng Song

1186SR-LSTM: State Refinement for LSTM Towards Pedestrian Trajectory Prediction






ThursdayPoster 3.2131Pu Zhang

1187Event Cameras, Contrast Maximization and Reward Functions: An Analysis






ThursdayPoster 3.2171Timo Stoffregen

1188Multi-Level Context Ultra-Aggregation for Stereo Matching






TuesdayPoster 1.281Guang-Yu Nie

1189Dense Depth Posterior (DDP) From Single Image and Sparse Range






TuesdayPoster 1.288Yanchao Yang

1190Large-Scale, Metric Structure From Motion for Unordered Light Fields






TuesdayPoster 1.282Sotiris Nousias

1191LSTA: Long Short-Term Attention for Egocentric Action Recognition






ThursdayPoster 3.1133Swathikiran Sudhakaran

1192Student Becoming the Master: Knowledge Amalgamation for Joint Scene Parsing, Depth Estimation, and More






TuesdayPoster 1.217Jingwen Ye

1193Feature Transfer Learning for Face Recognition With Under-Represented Data






WednesdayPoster 2.1131Xi Yin

1194Multi-Task Multi-Sensor Fusion for 3D Object Detection






WednesdayPoster 2.261Ming Liang

1195DuDoNet: Dual Domain Network for CT Metal Artifact Reduction






ThursdayPoster 3.1205Wei-An Lin

1196Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?






WednesdayPoster 2.137Shilin Zhu

1197Re-Identification Supervised Texture Generation






ThursdayPoster 3.289Jian Wang

1198Deep Spherical Quantization for Image Search






ThursdayPoster 3.273Sepehr Eghbali

1199Predicting Future Frames Using Retrospective Cycle GAN






TuesdayPoster 1.1183Yong-Hoon Kwon

1200Joint Representation and Estimator Learning for Facial Action Unit Intensity Estimation






TuesdayPoster 1.298Yong Zhang

1201MFAS: Multimodal Fusion Architecture Search






WednesdayPoster 2.24Juan-Manuel Perez-Rua

1202Feature Space Perturbations Yield More Transferable Adversarial Examples






WednesdayPoster 2.214Nathan Inkawhich

1203A Perceptual Prediction Framework for Self Supervised Event Segmentation






TuesdayPoster 1.1121Sathyanarayanan N. Aakur

1204Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection






ThursdayPoster 3.2187Taekyung Kim

1205Not All Frames Are Equal: Weakly-Supervised Video Grounding With Contextual Similarity and Visual Clustering Losses






ThursdayPoster 3.1183Jing Shi

1206Few-Shot Adaptive Faster R-CNN






WednesdayPoster 2.243Tao Wang

1207Multi-Scale Geometric Consistency Guided Multi-View Stereo






WednesdayPoster 2.194Qingshan Xu

1208Dense 3D Face Decoding Over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders






TuesdayPoster 1.199Yuxiang Zhou

1209An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition






TuesdayPoster 1.1124Chenyang Si

1210LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks






WednesdayPoster 2.135Sudhakar Kumawat

1212Adaptive Weighting Multi-Field-Of-View CNN for Semantic Segmentation in Pathology






ThursdayPoster 3.2201Hiroki Tokunaga

1213The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation






ThursdayPoster 3.284Dylan Campbell

1214PEPSI : Fast Image Inpainting With Parallel Decoding Network






ThursdayPoster 3.239Min-cheol Sagong

1215It's Not About the Journey; It's About the Destination: Following Soft Paths Under Question-Guidance for Visual Reasoning






TuesdayPoster 1.1195Monica Haurilet

1216Co-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing






TuesdayPoster 1.262Kaihua Zhang

1217Where's Wally Now? Deep Generative and Discriminative Embeddings for Novelty Detection






ThursdayPoster 3.254Philippe Burlina

1218Point-To-Pose Voting Based Hand Pose Estimation Using Residual Permutation Equivariant Layer






ThursdayPoster 3.2115Shile Li

1219Context-Reinforced Semantic Segmentation






TuesdayPoster 1.2194Yizhou Zhou

1220BridgeNet: A Continuity-Aware Probabilistic Network for Age Estimation






TuesdayPoster 1.1104Wanhua Li

1221DynTypo: Example-Based Dynamic Text Effects Transfer

https://menyifang.github.io/projects/DynTypo/DynTypo.html?



WednesdayPoster 2.1163Yifang MenYifang Men Zhouhui Lian Yingmin Tang Jianguo Xiao

1222StereoDRNet: Dilated Residual StereoNet






ThursdayPoster 3.283Rohan Chabra

1223Analysis of Feature Visibility in Non-Line-Of-Sight Measurements






ThursdayPoster 3.1152Xiaochun Liu

1225Unsupervised Event-Based Learning of Optical Flow, Depth, and Egomotion






TuesdayPoster 1.188Alex Zihao Zhu

1226Sensitive-Sample Fingerprinting of Deep Neural Networks






WednesdayPoster 2.117Zecheng He

1227Octree Guided CNN With Spherical Kernels for 3D Point Clouds






ThursdayPoster 3.1100Huan Lei

1228Assessment of Faster R-CNN in Man-Machine Collaborative Search






TuesdayPoster 1.271Arturo Deza

1229ADCrowdNet: An Attention-Injective Deformable Convolutional Network for Crowd Understanding






TuesdayPoster 1.275Ning Liu

1230Exact Adversarial Attack to Image Captioning via Structured Output Learning With Latent Variables






TuesdayPoster 1.2203Yan Xu

1231L3-Net: Towards Learning Based LiDAR Localization for Autonomous Driving






WednesdayPoster 2.1216Weixin Lu

1232Unsupervised Image Matching and Object Discovery as Optimization






WednesdayPoster 2.2175Huy V. Vo

1233P3SGD: Patient Privacy Preserving SGD for Regularizing Deep CNNs in Pathological Image Classification






TuesdayPoster 1.1212Bingzhe Wu

1234Self-Critical N-Step Training for Image Captioning






WednesdayPoster 2.1207Junlong Gao

1235ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation






WednesdayPoster 2.276Di Lin

1236DARNet: Deep Active Ray Network for Building Segmentation






WednesdayPoster 2.270Dominic Cheng

1237Efficient Multi-Domain Learning by Covariance Normalization






WednesdayPoster 2.188Yunsheng Li

1238Deep Fitting Degree Scoring Network for Monocular 3D Object Detection






TuesdayPoster 1.195Lijie Liu

1239Minimal Solvers for Mini-Loop Closures in 3D Multi-Scan Alignment






ThursdayPoster 3.1107Pedro Miraldo

1240A Robust Local Spectral Descriptor for Matching Non-Rigid Shapes With Incompatible Shape Structures






WednesdayPoster 2.1200Yiqun Wang

1241Local Temporal Bilinear Pooling for Fine-Grained Action Parsing






ThursdayPoster 3.2123Yan Zhang

1243Towards Optimal Structured CNN Pruning via Generative Adversarial Learning






TuesdayPoster 1.213Shaohui Lin

1244Semantically Aligned Bias Reducing Zero Shot Learning






WednesdayPoster 2.213Akanksha Paul

1245Synthesizing 3D Shapes From Silhouette Image Collections Using Multi-Projection Generative Adversarial Networks






WednesdayPoster 2.199Xiao Li

1246Temporal Cycle-Consistency Learning

https://sites.google.com/view/temporal-cycle-consistency?



TuesdayPoster 1.1182Debidatta DwibediDebidatta Dwibedi, Yusuf Aytar, Jonathan Tompson, Pierre Sermanet, Andrew Zisserman

1248DuLa-Net: A Dual-Projection Network for Estimating Room Layouts From a Single RGB Panorama






TuesdayPoster 1.289Shang-Ta Yang

1249Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing






TuesdayPoster 1.156Jiaxin Chen

1250Joint Representative Selection and Feature Learning: A Semi-Supervised Approach






WednesdayPoster 2.1177Suchen Wang

1251Connecting the Dots: Learning Representations for Active Monocular Depth Estimation






WednesdayPoster 2.290Gernot Riegler

1252Spot and Learn: A Maximum-Entropy Patch Sampler for Few-Shot Image Classification






WednesdayPoster 2.1202Wen-Hsuan Chu

1253An Alternative Deep Feature Approach to Line Level Keyword Spotting






ThursdayPoster 3.2207George Retsinas

1254RF-Net: An End-To-End Image Matching Network Based on Receptive Field






WednesdayPoster 2.2159Xuelun Shen

1255Self-Supervised Convolutional Subspace Clustering Network






WednesdayPoster 2.193Junjian Zhang

1256Generalizing Eye Tracking With Bayesian Adversarial Learning






ThursdayPoster 3.2113Kang Wang

1257Robust Video Stabilization by Optimization in CNN Weight Space






TuesdayPoster 1.2151Jiyang Yu

1258GIF2Video: Color Dequantization and Temporal Interpolation of GIF Images






TuesdayPoster 1.1143Yang Wang

1259DistillHash: Unsupervised Deep Hashing by Distilling Data Pairs






TuesdayPoster 1.247Erkun Yang

1260Multi-Person Articulated Tracking With Spatial and Temporal Embeddings






WednesdayPoster 2.1127Sheng Jin

1261Knowledge Adaptation for Efficient Semantic Segmentation






TuesdayPoster 1.135Tong He

1262Machine Vision Guided 3D Medical Image Compression for Efficient Transmission and Accurate Segmentation in the Clouds






ThursdayPoster 3.2210Zihao Liu

1263Interpreting CNNs via Decision Trees






WednesdayPoster 2.1203Quanshi Zhang

1264Surface Reconstruction From Normals: A Robust DGP-Based Discontinuity Preservation Approach






WednesdayPoster 2.178Wuyuan Xie

1265IGE-Net: Inverse Graphics Energy Networks for Human Pose Estimation and Single-View Reconstruction






WednesdayPoster 2.215Dominic Jack

1266Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Prediction






WednesdayPoster 2.222Osama Makansi

1267MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment






TuesdayPoster 1.1126Da ZhangDa Zhang, Xiyang Dai, Xin Wang, Yuan-Fang Wang, Larry S. Davis

1268End-To-End Learned Random Walker for Seeded Image Segmentation






ThursdayPoster 3.2197Lorenzo Cerrone

1269Object-Aware Aggregation With Bidirectional Temporal Graph for Video Captioning






WednesdayPoster 2.2197Junchao Zhang

1270Variational Convolutional Neural Network Pruning






TuesdayPoster 1.212Chenglong Zhao

1271Sequence-To-Sequence Domain Adaptation Network for Robust Text Image Recognition






TuesdayPoster 1.28Yaping Zhang

1272Structured Pruning of Neural Networks With Budget-Aware Regularization






ThursdayPoster 3.116Carl Lemaire

1273Exploring Object Relation in Mean Teacher for Cross-Domain Detection






ThursdayPoster 3.249Qi Cai

1274ROI-10D: Monocular Lifting of 2D Detection to 6D Pose and Metric Shape






TuesdayPoster 1.1209Fabian Manhardt

1275Douglas-Rachford Networks: Learning Both the Image Prior and Data Fidelity Terms for Blind Image Deconvolution






ThursdayPoster 3.1162Raied Aljadaany

1276Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation






ThursdayPoster 3.242Fengda Zhu

1278Orthogonal Decomposition Network for Pixel-Wise Binary Classification






WednesdayPoster 2.1183Chang Liu

1279Blind Image Deblurring With Local Maximum Gradient Prior






TuesdayPoster 1.1176Liang Chen

1280Emotion-Aware Human Attention Prediction






TuesdayPoster 1.2192Macario O. Cordel II

1281Spatio-Temporal Video Re-Localization by Warp LSTM






TuesdayPoster 1.1130Yang Feng

1282Deep Rigid Instance Scene Flow






TuesdayPoster 1.2114Wei-Chiu Ma

1283Exploring Context and Visual Pattern of Relationship for Scene Graph Generation






WednesdayPoster 2.2165Wenbin Wang

1284Normalized Diversification






ThursdayPoster 3.1169Shaohui Liu

1285SketchGAN: Joint Sketch Completion and Recognition With Generative Adversarial Network






WednesdayPoster 2.1159Fang Liu

1286Adaptive Transfer Network for Cross-Domain Person Re-Identification






WednesdayPoster 2.246Jiawei Liu

1287Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-Raining






WednesdayPoster 2.2205Rajeev Yasarla

1288Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction






TuesdayPoster 1.1179Yifei Shi

1289Retrieval-Augmented Convolutional Neural Networks Against Adversarial Examples






ThursdayPoster 3.260Jake Zhao (Junbo)

1290Visual Query Answering by Entity-Attribute Graph Matching and Reasoning






WednesdayPoster 2.2200Peixi Xiong

1292Monocular Depth Estimation Using Relative Depth Maps






ThursdayPoster 3.1110Jae-Han Lee

1293Variational Bayesian Dropout With a Hierarchical Prior






WednesdayPoster 2.220Yuhang Liu
Copyright oneie ©2014-2017 All Rights Reserved. 所有资料来源于互联网对相关版权责任概不负责。如发现侵犯了您的版权请与我们联系 QQ:86662817。 网际学院 版权所有 京ICP备14031243号-3
免责声明  商务合作及投稿请联系 QQ:86662817