Table of Contents

• SipMask: Spatial Information Preservation for Fast Image and Video Instance SegmentationJiale Cao, Rao Muhammad Anwer, Hisham Cholakkal, Fahad Shahbaz Khan, Yanwei Pang, Ling Shao 0001. 1-18 [doi]
• SemanticAdv: Generating Adversarial Examples via Attribute-Conditioned Image EditingHaonan Qiu, Chaowei Xiao, Lei Yang, Xinchen Yan, Honglak Lee, Bo Li. 19-37 [doi]
• Learning with Noisy Class Labels for Instance SegmentationLongrong Yang, Fanman Meng, Hongliang Li, Qingbo Wu 0001, Qishang Cheng. 38-53 [doi]
• Deep Image Clustering with Category-Style RepresentationJunJie Zhao, Donghuan Lu, Kai Ma, Yu Zhang, Yefeng Zheng. 54-70 [doi]
• Self-supervised Motion Representation via Scattering Local Motion CuesYuan Tian, Zhaohui Che, Wenbo Bao, Guangtao Zhai, Zhiyong Gao. 71-89 [doi]
• Improving Monocular Depth Estimation by Leveraging Structural Awareness and Complementary DatasetsTian Chen, Shijie An, Yuan Zhang, Chongyang Ma, Huayan Wang, Xiaoyan Guo, Wen Zheng. 90-108 [doi]
• BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video InterpolationJunheum Park, Keunsoo Ko, Chul Lee, Chang-Su Kim. 109-125 [doi]
• Hard Negative Examples are Hard, but UsefulHong Xuan, Abby Stylianou, Xiaotong Liu, Robert Pless. 126-142 [doi]
• ReActNet: Towards Precise Binary Neural Network with Generalized Activation FunctionsZechun Liu, Zhiqiang Shen, Marios Savvides, Kwang-Ting Cheng. 143-159 [doi]
• Video Object Detection via Object-Level Temporal AggregationChun-Han Yao, Chen Fang, Xiaohui Shen, Yangyue Wan, Ming-Hsuan Yang 0001. 160-177 [doi]
• Object Detection with a Unified Label Space from Multiple DatasetsXiangyun Zhao, Samuel Schulter, Gaurav Sharma, Yi-Hsuan Tsai, Manmohan Chandraker, Ying Wu. 178-193 [doi]
• Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3DJonah Philion, Sanja Fidler. 194-210 [doi]
• Comprehensive Image Captioning via Scene Graph DecompositionYiwu Zhong, Liwei Wang 0012, Jianshu Chen, Dong Yu 0001, Yin Li. 211-229 [doi]
• Symbiotic Adversarial Learning for Attribute-Based Person SearchYu-Tong Cao, Jingya Wang, Dacheng Tao. 230-247 [doi]
• Amplifying Key Cues for Human-Object-Interaction DetectionYang Liu 0105, Qingchao Chen, Andrew Zisserman. 248-265 [doi]
• Rethinking Few-Shot Image Classification: A Good Embedding is All You Need?Yonglong Tian, Yue Wang, Dilip Krishnan, Joshua B. Tenenbaum, Phillip Isola. 266-282 [doi]
• Adversarial Background-Aware Loss for Weakly-Supervised Temporal Activity LocalizationKyle Min, Jason J. Corso. 283-299 [doi]
• Action Localization Through Continual Predictive LearningSathyanarayanan N. Aakur, Sudeep Sarkar. 300-317 [doi]
• Generative View-Correlation Adaptation for Semi-supervised Multi-view LearningYunyu Liu, Lichen Wang, Yue Bai, Can Qin, Zhengming Ding, Yun Fu. 318-334 [doi]
• READ: Reciprocal Attention Discriminator for Image-to-Video Re-identificationMinho Shim, Hsuan-I Ho, Jinhyung Kim, Dongyoon Wee. 335-350 [doi]
• 3D Human Shape Reconstruction from a Polarization ImageShihao Zou, Xinxin Zuo, Yiming Qian, Sen Wang, Chi Xu, Minglun Gong, Li Cheng. 351-368 [doi]
• The Devil Is in the Details: Self-supervised Attention for Vehicle Re-identificationPirazh Khorramshahi, Neehar Peri, Jun-Cheng Chen, Rama Chellappa. 369-386 [doi]
• Improving One-Stage Visual Grounding by Recursive Sub-query ConstructionZhengyuan Yang, Tianlang Chen, Liwei Wang 0012, Jiebo Luo. 387-404 [doi]
• Multi-level Wavelet-Based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed VideoJianyi Wang, Xin Deng 0002, Mai Xu, Congyong Chen, Yuhang Song 0001. 405-421 [doi]
• Example-Guided Image Synthesis Using Masked Spatial-Channel Attention and Self-supervisionHaitian Zheng, Haofu Liao, Lele Chen, Wei Xiong 0008, Tianlang Chen, Jiebo Luo. 422-439 [doi]
• Content-Consistent Matching for Domain Adaptive Semantic SegmentationGuangrui Li 0005, Guoliang Kang, Wu Liu, Yunchao Wei, Yi Yang. 440-456 [doi]
• AE TextSpotter: Learning Visual and Linguistic Representation for Ambiguous Text SpottingWenhai Wang, Xuebo Liu 0001, Xiaozhong Ji, Enze Xie, Ding Liang, Zhibo Yang, Tong Lu, Chunhua Shen, Ping Luo. 457-473 [doi]
• History Repeats Itself: Human Motion Prediction via Motion AttentionWei Mao, Miaomiao Liu, Mathieu Salzmann. 474-489 [doi]
• Unsupervised Video Object Segmentation with Joint Hotspot TrackingLu Zhang, Jianming Zhang, Zhe Lin, Radomír Mech, Huchuan Lu, You He. 490-506 [doi]
• SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine ApproachAiling Zeng, Xiao Sun, Fuyang Huang, Minhao Liu, Qiang Xu, Stephen Lin. 507-523 [doi]
• CAFE-GAN: Arbitrary Face Attribute Editing with Complementary Attention FeatureJeong-gi Kwak, David K. Han, Hanseok Ko. 524-540 [doi]
• MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object DetectionXin Lu, Quanquan Li, Buyu Li, Junjie Yan. 541-557 [doi]
• Latent Topic-Aware Multi-label ClassificationJianghong Ma, Yang Liu 0061. 558-573 [doi]
• Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change CaptioningXiangxi Shi, Xu Yang, Jiuxiang Gu, Shafiq R. Joty, Jianfei Cai 0001. 574-590 [doi]
• Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain AdaptationTaekyung Kim, Changick Kim. 591-607 [doi]
• Curriculum Manager for Source Selection in Multi-source Domain AdaptationLuyu Yang, Yogesh Balaji, Ser-Nam Lim, Abhinav Shrivastava. 608-624 [doi]
• Powering One-Shot Topological NAS with Stabilized Share-Parameter ProxyRonghao Guo, Chen Lin, Chuming Li, Keyu Tian, Ming Sun, Lu Sheng, Junjie Yan. 625-641 [doi]
• Classes Matter: A Fine-Grained Adversarial Approach to Cross-Domain Semantic SegmentationHaoran Wang, Tong Shen, Wei Zhang, Ling-Yu Duan, Tao Mei 0001. 642-659 [doi]
• Boundary-Preserving Mask R-CNNTianheng Cheng, Xinggang Wang, Lichao Huang, Wenyu Liu 0001. 660-676 [doi]
• Self-supervised Single-View 3D Reconstruction via Semantic ConsistencyXueting Li, Sifei Liu, Kihwan Kim, Shalini De Mello, Varun Jampani, Ming-Hsuan Yang 0001, Jan Kautz. 677-693 [doi]
• MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down DistillationBenlin Liu, Yongming Rao, Jiwen Lu, Jie Zhou 0001, Cho-Jui Hsieh. 694-709 [doi]
• Learning Monocular Visual Odometry via Self-Supervised Long-Term ModelingYuliang Zou, Pan Ji, Quoc Huy Tran, Jia-Bin Huang, Manmohan Chandraker. 710-727 [doi]
• The Devil Is in Classification: A Simple Framework for Long-Tail Instance SegmentationTao Wang, Yu Li, Bingyi Kang, Junnan Li, Jun Hao Liew, Sheng Tang, Steven C. H. Hoi, Jiashi Feng. 728-744 [doi]
• What Is Learned in Deep Uncalibrated Photometric Stereo?Guanying Chen, Michael Waechter, Boxin Shi, Kwan-Yee K. Wong, Yasuyuki Matsushita. 745-762 [doi]
• Prior-Based Domain Adaptive Object Detection for Hazy and Rainy ConditionsVishwanath A. Sindagi, Poojan Oza, Rajeev Yasarla, Vishal M. Patel. 763-780 [doi]
• Adversarial Ranking Attack and DefenseMo Zhou, Zhenxing Niu, Le Wang 0003, Qilin Zhang, Gang Hua 0001. 781-799 [doi]