Table of Contents

• ReDro: Efficiently Learning Large-Sized SPD Visual RepresentationSaimunur Rahman, Lei Wang 0001, Changming Sun, Luping Zhou. 1-17 [doi]
• Graph-Based Social Relation ReasoningWanhua Li, Yueqi Duan, Jiwen Lu, Jianjiang Feng, Jie Zhou 0001. 18-34 [doi]
• EPNet: Enhancing Point Features with Image Semantics for 3D Object DetectionTengteng Huang, Zhe Liu, Xiwu Chen, Xiang Bai. 35-52 [doi]
• Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry ConsistencyJiaxiang Shang, Tianwei Shen, Shiwei Li, Lei Zhou, Mingmin Zhen, Tian Fang, Long Quan. 53-70 [doi]
• Asynchronous Interaction Aggregation for Action DetectionJiajun Tang, Jin Xia, Xinzhi Mu, Bo Pang, Cewu Lu. 71-87 [doi]
• Shape and Viewpoint Without KeypointsShubham Goel, Angjoo Kanazawa, Jitendra Malik. 88-104 [doi]
• Learning Attentive and Hierarchical Representations for 3D Shape RecognitionJiaxin Chen, Jie Qin, Yuming Shen, Li Liu 0004, Fan Zhu 0001, Ling Shao 0001. 105-122 [doi]
• TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture SearchYibo Hu, Xiang Wu 0001, Ran He. 123-139 [doi]
• Associative3D: Volumetric Reconstruction from Sparse ViewsShengyi Qian 0001, Linyi Jin, David F. Fouhey. 140-157 [doi]
• PlugNet: Degradation Aware Scene Text Recognition Supervised by a Pluggable Super-Resolution UnitYongqiang Mou, Lei Tan, Hui Yang, Jingying Chen, Leyuan Liu, Rui Yan, Yaohong Huang. 158-174 [doi]
• Memory Selection Network for Video PropagationRuizheng Wu, Huaijia Lin, Xiaojuan Qi, Jiaya Jia. 175-190 [doi]
• Disentangled Non-local Neural NetworksMinghao Yin, Zhuliang Yao, Yue Cao 0001, Xiu Li, Zheng Zhang 0022, Stephen Lin, Han Hu. 191-207 [doi]
• URVOS: Unified Referring Video Object Segmentation Network with a Large-Scale BenchmarkSeonguk Seo, Joon-Young Lee, Bohyung Han. 208-223 [doi]
• Generalizing Person Re-Identification by Camera-Aware Invariance Learning and Cross-Domain MixupChuanchen Luo, Chunfeng Song, Zhaoxiang Zhang. 224-241 [doi]
• Semi-supervised Crowd Counting via Self-training on Surrogate TasksYan Liu 0015, Lingqiao Liu, Peng Wang 0023, Pingping Zhang, Yinjie Lei. 242-259 [doi]
• Dynamic R-CNN: Towards High Quality Object Detection via Dynamic TrainingHongkai Zhang, Hong Chang, Bingpeng Ma, Naiyan Wang, Xilin Chen. 260-275 [doi]
• Boosting Decision-Based Black-Box Adversarial Attacks with Random Sign FlipWeilun Chen, Zhaoxiang Zhang, Xiaolin Hu, Baoyuan Wu. 276-293 [doi]
• Knowledge Transfer via Dense Cross-Layer Mutual-DistillationAnbang Yao, Dawei Sun. 294-311 [doi]
• Matching Guided DistillationKaiyu Yue, Jiangfan Deng, Feng Zhou 0002. 312-328 [doi]
• Clustering Driven Deep Autoencoder for Video Anomaly DetectionYunpeng Chang, Zhigang Tu 0001, Wei Xie, Junsong Yuan. 329-345 [doi]
• Learning to Compose Hypercolumns for Visual CorrespondenceJuhong Min, Jongmin Lee 0005, Jean Ponce, Minsu Cho. 346-363 [doi]
• Stochastic Bundle Adjustment for Efficient and Scalable 3D ReconstructionLei Zhou, Zixin Luo, Mingmin Zhen, Tianwei Shen, Shiwei Li, Zhuofei Huang, Tian Fang, Long Quan. 364-379 [doi]
• Object-Based Illumination Estimation with Rendering-Aware Neural NetworksXin Wei, Guojun Chen, Yue Dong, Stephen Lin, Xin Tong 0001. 380-396 [doi]
• Progressive Point Cloud Deconvolution Generation NetworkLe Hui, Rui Xu, Jin Xie, Jianjun Qian, Jian Yang 0003. 397-413 [doi]
• SSCGAN: Facial Attribute Editing via Style Skip ConnectionsWenqing Chu, Ying Tai, Chengjie Wang, Jilin Li, Feiyue Huang, Rongrong Ji. 414-429 [doi]
• Negative Pseudo Labeling Using Class Proportion for Semantic Segmentation in PathologyHiroki Tokunaga, Brian Kenji Iwana, Yuki Teramoto, Akihiko Yoshizawa, Ryoma Bise. 430-446 [doi]
• Learn to Propagate Reliably on Noisy Affinity GraphsLei Yang, Qingqiu Huang, Huaiyi Huang, Linning Xu, Dahua Lin. 447-464 [doi]
• Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture SearchXiangxiang Chu, Tianbao Zhou, Bo Zhang 0046, Jixiang Li. 465-480 [doi]
• TANet: Towards Fully Automatic Tooth ArrangementGuodong Wei, Zhiming Cui, Yumeng Liu, Nenglun Chen, Runnan Chen, Guiqing Li, Wenping Wang. 481-497 [doi]
• UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction DetectionBumsoo Kim, Taeho Choi, Jaewoo Kang, Hyunwoo J. Kim. 498-514 [doi]
• GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-Aware SupervisionLei Ke, Shichao Li, Yanan Sun, Yu-Wing Tai, Chi-Keung Tang. 515-532 [doi]
• Resolution Switchable Networks for Runtime Efficient Image RecognitionYikai Wang, Fuchun Sun, Duo Li, Anbang Yao. 533-549 [doi]
• SMAP: Single-Shot Multi-person Absolute 3D Pose EstimationJianan Zhen, Qi Fang, Jiaming Sun, Wentao Liu 0002, Wei Jiang, Hujun Bao, Xiaowei Zhou. 550-566 [doi]
• Learning to Detect Open Classes for Universal Domain AdaptationBo Fu, Zhangjie Cao, Mingsheng Long, Jianmin Wang 0001. 567-583 [doi]
• Visual Compositional Learning for Human-Object Interaction DetectionZhi Hou, Xiaojiang Peng, Yu Qiao 0001, Dacheng Tao. 584-600 [doi]
• Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn SketchesShuai Yang 0001, Zhangyang Wang, Jiaying Liu 0001, Zongming Guo. 601-617 [doi]
• Rethinking Class Activation Mapping for Weakly Supervised Object LocalizationWonho Bae, Junhyug Noh, Gunhee Kim. 618-634 [doi]
• OS2D: One-Stage One-Shot Object Detection by Matching Anchor FeaturesAnton Osokin, Denis Sumin, Vasily Lomakin. 635-652 [doi]
• Interpretable Neural Network DecouplingYuchao Li, Rongrong Ji, Shaohui Lin, Baochang Zhang 0001, Chenqian Yan, Yongjian Wu, Feiyue Huang, Ling Shao 0001. 653-669 [doi]
• Omni-Sourced Webly-Supervised Learning for Video RecognitionHaodong Duan, Yue Zhao 0006, Yuanjun Xiong, Wentao Liu 0002, Dahua Lin. 670-688 [doi]
• CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point BlendingHang Xu, Shaoju Wang, Xinyue Cai, Wei Zhang, Xiaodan Liang, Zhenguo Li. 689-704 [doi]
• Contextual-Relation Consistent Domain Adaptation for Semantic SegmentationJiaxing Huang, Shijian Lu, Dayan Guan, Xiaobing Zhang. 705-722 [doi]
• Estimating People Flows to Better Count Them in Crowded ScenesWeizhe Liu, Mathieu Salzmann, Pascal Fua. 723-740 [doi]
• Generate to Adapt: Resolution Adaption Network for Surveillance Face RecognitionHan Fang, Weihong Deng, Yaoyao Zhong, Jiani Hu. 741-758 [doi]
• Learning Feature Embeddings for Discriminant Model Based TrackingLinyu Zheng, Ming Tang, Yingying Chen 0003, Jinqiao Wang, Hanqing Lu. 759-775 [doi]
• WeightNet: Revisiting the Design Space of Weight NetworksNingning Ma, Xiangyu Zhang 0005, Jiawei Huang, Jian Sun 0015. 776-792 [doi]