1. Home
  2. Proceedings
  3. CVPR
  4. CVPR 2020
Default Cover Image

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

June 13 2020 to June 19 2020

Seattle, WA, USA

ISBN: 978-1-7281-7168-5

Table of Contents

Title Page iFreely available from IEEE.pp. 1-1
Title Page iiiFreely available from IEEE.pp. 3-3
Copyright PageFreely available from IEEE.pp. 4-4
Table of ContentsFreely available from IEEE.pp. 5-208
OrganizersFreely available from IEEE.pp. 209-210
Area ChairsFreely available from IEEE.pp. 211-215
ReviewersFreely available from IEEE.pp. 216-216
Unsupervised Learning of Probably Symmetric Deformable 3D Objects From Images in the WildFull-text access may be available. Sign in or learn about subscription options.pp. 1-10
by Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
Footprints and Free Space From a Single Color ImageFull-text access may be available. Sign in or learn about subscription options.pp. 11-20
by Jamie Watson, Michael Firman, Aron Monszpart, Gabriel J. Brostow
Dynamic Fluid Surface Reconstruction Using Deep Neural NetworkFull-text access may be available. Sign in or learn about subscription options.pp. 21-30
by Simron Thapa, Nianyi Li, Jinwei Ye
CvxNet: Learnable Convex DecompositionFull-text access may be available. Sign in or learn about subscription options.pp. 31-41
by Boyang Deng, Kyle Genova, Soroosh Yazdani, Sofien Bouaziz, Geoffrey Hinton, Andrea Tagliasacchi
BSP-Net: Generating Compact Meshes via Binary Space PartitioningFull-text access may be available. Sign in or learn about subscription options.pp. 42-51
by Zhiqin Chen, Andrea Tagliasacchi, Hao Zhang
Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes From a Single ImageFull-text access may be available. Sign in or learn about subscription options.pp. 52-61
by Yinyu Nie, Xiaoguang Han, Shihui Guo, Yujian Zheng, Jian Chang, Jian Jun Zhang
Generating and Exploiting Probabilistic Monocular Depth EstimatesFull-text access may be available. Sign in or learn about subscription options.pp. 62-71
by Zhihao Xia, Patrick Sullivan, Ayan Chakrabarti
Neural Cages for Detail-Preserving 3D DeformationsFull-text access may be available. Sign in or learn about subscription options.pp. 72-80
by Wang Yifan, Noam Aigerman, Vladimir G. Kim, Siddhartha Chaudhuri, Olga Sorkine-Hornung
PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human DigitizationFull-text access may be available. Sign in or learn about subscription options.pp. 81-90
by Shunsuke Saito, Tomas Simon, Jason Saragih, Hanbyul Joo
A Lighting-Invariant Point Processor for ShadingFull-text access may be available. Sign in or learn about subscription options.pp. 91-99
by Kathryn Heal, Jialiang Wang, Steven J. Gortler, Todd Zickler
ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion CaptureFull-text access may be available. Sign in or learn about subscription options.pp. 100-109
by Sena Kiciroglu, Helge Rhodin, Sudipta N. Sinha, Mathieu Salzmann, Pascal Fua
Peek-a-Boo: Occlusion Reasoning in Indoor Scenes With Plane RepresentationsFull-text access may be available. Sign in or learn about subscription options.pp. 110-118
by Ziyu Jiang, Buyu Liu, Samuel Schulter, Zhangyang Wang, Manmohan Chandraker
Multi-Modal Domain Adaptation for Fine-Grained Action RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 119-129
by Jonathan Munro, Dima Damen
Evolving Losses for Unsupervised Video Representation LearningFull-text access may be available. Sign in or learn about subscription options.pp. 130-139
by AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 140-149
by Ziyu Liu, Hongwen Zhang, Zhenghao Chen, Zhiyong Wang, Wanli Ouyang
A Multigrid Method for Efficiently Training Video ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 150-159
by Chao-Yuan Wu, Ross Girshick, Kaiming He, Christoph Feichtenhofer, Philipp Krähenbühl
Ego-Topo: Environment Affordances From Egocentric VideoFull-text access may be available. Sign in or learn about subscription options.pp. 160-169
by Tushar Nagarajan, Yanghao Li, Christoph Feichtenhofer, Kristen Grauman
Generative Hybrid Representations for Activity Forecasting With No-Regret LearningFull-text access may be available. Sign in or learn about subscription options.pp. 170-179
by Jiaqi Guan, Ye Yuan, Kris M. Kitani, Nicholas Rhinehart
Skeleton-Based Action Recognition With Shift Graph Convolutional NetworkFull-text access may be available. Sign in or learn about subscription options.pp. 180-189
by Ke Cheng, Yifan Zhang, Xiangyu He, Weihan Chen, Jian Cheng, Hanqing Lu
Predicting Goal-Directed Human Attention Using Inverse Reinforcement LearningFull-text access may be available. Sign in or learn about subscription options.pp. 190-199
by Zhibo Yang, Lihan Huang, Yupei Chen, Zijun Wei, Seoyoung Ahn, Gregory Zelinsky, Dimitris Samaras, Minh Hoai
X3D: Expanding Architectures for Efficient Video RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 200-210
by Christoph Feichtenhofer
Dynamic Multiscale Graph Neural Networks for 3D Skeleton Based Human Motion PredictionFull-text access may be available. Sign in or learn about subscription options.pp. 211-220
by Maosen Li, Siheng Chen, Yangheng Zhao, Ya Zhang, Yanfeng Wang, Qi Tian
Use the Force, Luke! Learning to Predict Physical Forces by Simulating EffectsFull-text access may be available. Sign in or learn about subscription options.pp. 221-230
by Kiana Ehsani, Shubham Tulsiani, Saurabh Gupta, Ali Farhadi, Abhinav Gupta
DaST: Data-Free Substitute Training for Adversarial AttacksFull-text access may be available. Sign in or learn about subscription options.pp. 231-240
by Mingyi Zhou, Jing Wu, Yipeng Liu, Shuaicheng Liu, Ce Zhu
Towards Verifying Robustness of Neural Networks Against A Family of Semantic PerturbationsFull-text access may be available. Sign in or learn about subscription options.pp. 241-249
by Jeet Mohapatra, Tsui-Wei Weng, Pin-Yu Chen, Sijia Liu, Luca Daniel
The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 250-258
by Yuheng Zhang, Ruoxi Jia, Hengzhi Pei, Wenxiao Wang, Bo Li, Dawn Song
A Self-supervised Approach for Adversarial RobustnessFull-text access may be available. Sign in or learn about subscription options.pp. 259-268
by Muzammal Naseer, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Fatih Porikli
Adversarial Vertex Mixup: Toward Better Adversarially Robust GeneralizationFull-text access may be available. Sign in or learn about subscription options.pp. 269-278
by Saehyung Lee, Hyungyu Lee, Sungroh Yoon
How Does Noise Help Robustness? Explanation and Exploration under the Neural SDE FrameworkFull-text access may be available. Sign in or learn about subscription options.pp. 279-287
by Xuanqing Liu, Tesi Xiao, Si Si, Qin Cao, Sanjiv Kumar, Cho-Jui Hsieh
Unpaired Image Super-Resolution Using Pseudo-SupervisionFull-text access may be available. Sign in or learn about subscription options.pp. 288-297
by Shunta Maeda
Universal Litmus Patterns: Revealing Backdoor Attacks in CNNsFull-text access may be available. Sign in or learn about subscription options.pp. 298-307
by Soheil Kolouri, Aniruddha Saha, Hamed Pirsiavash, Heiko Hoffmann
Robustness Guarantees for Deep Neural Networks on VideosFull-text access may be available. Sign in or learn about subscription options.pp. 308-317
by Min Wu, Marta Kwiatkowska
Benchmarking Adversarial Robustness on Image ClassificationFull-text access may be available. Sign in or learn about subscription options.pp. 318-328
by Yinpeng Dong, Qi-An Fu, Xiao Yang, Tianyu Pang, Hang Su, Zihao Xiao, Jun Zhu
What It Thinks Is Important Is Important: Robustness Transfers Through Input GradientsFull-text access may be available. Sign in or learn about subscription options.pp. 329-338
by Alvin Chan, Yi Tay, Yew-Soon Ong
Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-RankingFull-text access may be available. Sign in or learn about subscription options.pp. 339-348
by Hongjun Wang, Guangrun Wang, Ya Li, Dongyu Zhang, Liang Lin
Video Modeling With Correlation NetworksFull-text access may be available. Sign in or learn about subscription options.pp. 349-358
by Heng Wang, Du Tran, Lorenzo Torresani, Matt Feiszli
Projection & Probability-Driven Black-Box AttackFull-text access may be available. Sign in or learn about subscription options.pp. 359-368
by Jie Li, Rongrong Ji, Hong Liu, Jianzhuang Liu, Bineng Zhong, Cheng Deng, Qi Tian
Auxiliary Training: Towards Accurate and Robust ModelsFull-text access may be available. Sign in or learn about subscription options.pp. 369-378
by Linfeng Zhang, Muzhou Yu, Tong Chen, Zuoqiang Shi, Chenglong Bao, Kaisheng Ma
PaStaNet: Toward Human Activity Knowledge EngineFull-text access may be available. Sign in or learn about subscription options.pp. 379-388
by Yong-Lu Li, Liang Xu, Xinpeng Liu, Xijie Huang, Yue Xu, Shiyi Wang, Hao-Shu Fang, Ze Ma, Mingyang Chen, Cewu Lu
A Hierarchical Graph Network for 3D Object Detection on Point CloudsFull-text access may be available. Sign in or learn about subscription options.pp. 389-398
by Jintai Chen, Biwen Lei, Qingyu Song, Haochao Ying, Danny Z. Chen, Jian Wu
Learning Generative Models of Shape HandlesFull-text access may be available. Sign in or learn about subscription options.pp. 399-408
by Matheus Gadelha, Giorgio Gori, Duygu Ceylan, Radomír Měch, Nathan Carr, Tamy Boubekeur, Rui Wang, Subhransu Maji
One Man’s Trash Is Another Man’s Treasure: Resisting Adversarial Examples by Adversarial ExamplesFull-text access may be available. Sign in or learn about subscription options.pp. 409-418
by Chang Xiao, Changxi Zheng
Toward a Universal Model for Shape From TextureFull-text access may be available. Sign in or learn about subscription options.pp. 419-427
by Dor Verbin, Todd Zickler
HybridPose: 6D Object Pose Estimation Under Hybrid RepresentationsFull-text access may be available. Sign in or learn about subscription options.pp. 428-437
by Chen Song, Jiaru Song, Qixing Huang
Boundary-Aware 3D Building Reconstruction From a Single Overhead ImageFull-text access may be available. Sign in or learn about subscription options.pp. 438-448
by Jisan Mahmud, TRUE Price, Akash Bapat, Jan-Michael Frahm
Articulation-Aware Canonical Surface MappingFull-text access may be available. Sign in or learn about subscription options.pp. 449-458
by Nilesh Kulkarni, Abhinav Gupta, David F. Fouhey, Shubham Tulsiani
BiFuse: Monocular 360 Depth Estimation via Bi-Projection FusionFull-text access may be available. Sign in or learn about subscription options.pp. 459-468
by Fu-En Wang, Yu-Hsuan Yeh, Min Sun, Wei-Chen Chiu, Yi-Hsuan Tsai
Transformation GAN for Unsupervised Image Synthesis and Representation LearningFull-text access may be available. Sign in or learn about subscription options.pp. 469-478
by Jiayu Wang, Wengang Zhou, Guo-Jun Qi, Zhongqian Fu, Qi Tian, Houqiang Li
PPDM: Parallel Point Detection and Matching for Real-Time Human-Object Interaction DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 479-487
by Yue Liao, Si Liu, Fei Wang, Yanjie Chen, Chen Qian, Jiashi Feng
Height and Uprightness Invariance for 3D Prediction From a Single ViewFull-text access may be available. Sign in or learn about subscription options.pp. 488-497
by Manel Baradad, Antonio Torralba
SCT: Set Constrained Temporal Transformer for Set Supervised Action SegmentationFull-text access may be available. Sign in or learn about subscription options.pp. 498-507
by Mohsen Fayyaz, Jürgen Gall
3DV: 3D Dynamic Voxel for Action Recognition in Depth VideoFull-text access may be available. Sign in or learn about subscription options.pp. 508-517
by Yancheng Wang, Yang Xiao, Fu Xiong, Wenxiang Jiang, Zhiguo Cao, Joey Tianyi Zhou, Junsong Yuan
Adaptive Interaction Modeling via Graph Operations SearchFull-text access may be available. Sign in or learn about subscription options.pp. 518-527
by Haoxin Li, Wei-Shi Zheng, Yu Tao, Haifeng Hu, Jian-Huang Lai
Front2Back: Single View 3D Shape Reconstruction via Front to Back PredictionFull-text access may be available. Sign in or learn about subscription options.pp. 528-537
by Yuan Yao, Nico Schertler, Enrique Rosales, Helge Rhodin, Leonid Sigal, Alla Sheffer
SDC-Depth: Semantic Divide-and-Conquer Network for Monocular Depth EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 538-547
by Lijun Wang, Jianming Zhang, Oliver Wang, Zhe Lin, Huchuan Lu
Single-View View Synthesis With Multiplane ImagesFull-text access may be available. Sign in or learn about subscription options.pp. 548-557
by Richard Tucker, Noah Snavely
Deep Parametric Shape Predictions Using Distance FieldsFull-text access may be available. Sign in or learn about subscription options.pp. 558-567
by Dmitriy Smirnov, Matthew Fisher, Vladimir G. Kim, Richard Zhang, Justin Solomon
Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object ReconstructionFull-text access may be available. Sign in or learn about subscription options.pp. 568-577
by Yana Hasson, Bugra Tekin, Federica Bogo, Ivan Laptev, Marc Pollefeys, Cordelia Schmid
Ensemble Generative Cleaning With Feedback Loops for Defending Adversarial AttacksFull-text access may be available. Sign in or learn about subscription options.pp. 578-587
by Jianhe Yuan, Zhihai He
Temporal Pyramid Network for Action RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 588-597
by Ceyuan Yang, Yinghao Xu, Jianping Shi, Bo Dai, Bolei Zhou
FaceScape: A Large-Scale High Quality 3D Face Dataset and Detailed Riggable 3D Face PredictionFull-text access may be available. Sign in or learn about subscription options.pp. 598-607
by Haotian Yang, Hao Zhu, Yanru Wang, Mingkai Huang, Qiu Shen, Ruigang Yang, Xun Cao
Structure-Guided Ranking Loss for Single Image Depth PredictionFull-text access may be available. Sign in or learn about subscription options.pp. 608-617
by Ke Xian, Jianming Zhang, Oliver Wang, Long Mai, Zhe Lin, Zhiguo Cao
In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction From 2D LandmarksFull-text access may be available. Sign in or learn about subscription options.pp. 618-627
by Heng Yang, Luca Carlone
When NAS Meets Robustness: In Search of Robust Architectures Against Adversarial AttacksFull-text access may be available. Sign in or learn about subscription options.pp. 628-637
by Minghao Guo, Yuzhe Yang, Rui Xu, Ziwei Liu, Dahua Lin
Towards Transferable Targeted AttackFull-text access may be available. Sign in or learn about subscription options.pp. 638-646
by Maosen Li, Cheng Deng, Tengjiao Li, Junchi Yan, Xinbo Gao, Heng Huang
Self-Supervised Human Depth Estimation From Monocular VideosFull-text access may be available. Sign in or learn about subscription options.pp. 647-656
by Feitong Tan, Hao Zhu, Zhaopeng Cui, Siyu Zhu, Marc Pollefeys, Ping Tan
Recursive Social Behavior Graph for Trajectory PredictionFull-text access may be available. Sign in or learn about subscription options.pp. 657-666
by Jianhua Sun, Qinhong Jiang, Cewu Lu
Context-Aware and Scale-Insensitive Temporal Repetition CountingFull-text access may be available. Sign in or learn about subscription options.pp. 667-675
by Huaidong Zhang, Xuemiao Xu, Guoqiang Han, Shengfeng He
OASIS: A Large-Scale Dataset for Single Image 3D in the WildFull-text access may be available. Sign in or learn about subscription options.pp. 676-685
by Weifeng Chen, Shengyi Qian, David Fan, Noriyuki Kojima, Max Hamilton, Jia Deng
VPLNet: Deep Single View Normal Estimation With Vanishing Points and LinesFull-text access may be available. Sign in or learn about subscription options.pp. 686-695
by Rui Wang, David Geraghty, Kevin Matzen, Richard Szeliski, Jan-Michael Frahm
Adversarial Robustness: From Self-Supervised Pre-Training to Fine-TuningFull-text access may be available. Sign in or learn about subscription options.pp. 696-705
by Tianlong Chen, Sijia Liu, Shiyu Chang, Yu Cheng, Lisa Amini, Zhangyang Wang
Defending Against Universal Attacks Through Selective Feature RegenerationFull-text access may be available. Sign in or learn about subscription options.pp. 706-716
by Tejas Borkar, Felix Heide, Lina Karam
Universal Physical Camouflage Attacks on Object DetectorsFull-text access may be available. Sign in or learn about subscription options.pp. 717-726
by Lifeng Huang, Chengying Gao, Yuyin Zhou, Cihang Xie, Alan L. Yuille, Changqing Zou, Ning Liu
Intra- and Inter-Action Understanding via Temporal Action ParsingFull-text access may be available. Sign in or learn about subscription options.pp. 727-736
by Dian Shao, Yue Zhao, Bo Dai, Dahua Lin
Lightweight Photometric Stereo for Facial Details RecoveryFull-text access may be available. Sign in or learn about subscription options.pp. 737-746
by Xueying Wang, Yudong Guo, Bailin Deng, Juyong Zhang
Bundle Pooling for Polygonal Architecture Segmentation ProblemFull-text access may be available. Sign in or learn about subscription options.pp. 747-756
by Huayi Zeng, Kevin Joseph, Adam Vest, Yasutaka Furukawa
AvatarMe: Realistically Renderable 3D Facial Reconstruction “In-the-Wild”Full-text access may be available. Sign in or learn about subscription options.pp. 757-766
by Alexandros Lattas, Stylianos Moschoglou, Baris Gecer, Stylianos Ploumpis, Vasileios Triantafyllou, Abhijeet Ghosh, Stefanos Zafeiriou
Defending Against Model Stealing Attacks With Adaptive MisinformationFull-text access may be available. Sign in or learn about subscription options.pp. 767-775
by Sanjay Kariyappa, Moinuddin K. Qureshi
Learning to Generate 3D Training Data Through Hybrid GradientFull-text access may be available. Sign in or learn about subscription options.pp. 776-786
by Dawei Yang, Jia Deng
Cascaded Refinement Network for Point Cloud CompletionFull-text access may be available. Sign in or learn about subscription options.pp. 787-796
by Xiaogang Wang, Marcelo H. Ang, Gim Hee Lee
Enhancing Intrinsic Adversarial Robustness via Feature Pyramid DecoderFull-text access may be available. Sign in or learn about subscription options.pp. 797-805
by Guanlin Li, Shuya Ding, Jun Luo, Chang Liu
Learning to Discriminate Information for Online Action DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 806-815
by Hyunjun Eun, Jinyoung Moon, Jongyoul Park, Chanho Jung, Changick Kim
Adversarial Examples Improve Image RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 816-825
by Cihang Xie, Mingxing Tan, Boqing Gong, Jiang Wang, Alan L. Yuille, Quoc V. Le
PQ-NET: A Generative Part Seq2Seq Network for 3D ShapesFull-text access may be available. Sign in or learn about subscription options.pp. 826-835
by Rundi Wu, Yixin Zhuang, Kai Xu, Hao Zhang, Baoquan Chen
Actor-Transformers for Group Activity RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 836-845
by Kirill Gavrilyuk, Ryan Sanford, Mehrsan Javan, Cees G. M. Snoek
SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D ScansFull-text access may be available. Sign in or learn about subscription options.pp. 846-855
by Angela Dai, Christian Diller, Matthias Niessner
Geometry-Aware Satellite-to-Ground Image Synthesis for Urban AreasFull-text access may be available. Sign in or learn about subscription options.pp. 856-864
by Xiaohu Lu, Zuoyue Li, Zhaopeng Cui, Martin R. Oswald, Marc Pollefeys, Rongjun Qin
Action Modifiers: Learning From Adverbs in Instructional VideosFull-text access may be available. Sign in or learn about subscription options.pp. 865-875
by Hazel Doughty, Ivan Laptev, Walterio Mayol-Cuevas, Dima Damen
ZSTAD: Zero-Shot Temporal Activity DetectionFull-text access may be available. Sign in or learn about subscription options.pp. 876-885
by Lingling Zhang, Xiaojun Chang, Jun Liu, Minnan Luo, Sen Wang, Zongyuan Ge, Alexander Hauptmann
Geometric Structure Based and Regularized Depth Estimation From 360 Indoor ImageryFull-text access may be available. Sign in or learn about subscription options.pp. 886-895
by Lei Jin, Yanyu Xu, Jia Zheng, Junfei Zhang, Rui Tang, Shugong Xu, Jingyi Yu, Shenghua Gao
Deep Kinematics Analysis for Monocular 3D Human Pose EstimationFull-text access may be available. Sign in or learn about subscription options.pp. 896-905
by Jingwei Xu, Zhenbo Yu, Bingbing Ni, Jiancheng Yang, Xiaokang Yang, Wenjun Zhang
TEA: Temporal Excitation and Aggregation for Action RecognitionFull-text access may be available. Sign in or learn about subscription options.pp. 906-915
by Yan Li, Bin Ji, Xintian Shi, Jianguo Zhang, Bin Kang, Limin Wang
Oops! Predicting Unintentional Action in VideoFull-text access may be available. Sign in or learn about subscription options.pp. 916-926
by Dave Epstein, Boyuan Chen, Carl Vondrick
Showing 100 out of 1473
Load More
Load All