Table of Contents

• Expanding Language-Image Pretrained Models for General Video RecognitionBolin Ni, Houwen Peng, Minghao Chen, Songyang Zhang, Gaofeng Meng, Jianlong Fu, Shiming Xiang, Haibin Ling. 1-18 [doi]
• Hunting Group Clues with Transformers for Social Group Activity RecognitionMasato Tamura, Rahul Vishwakarma, Ravigopal Vennelakanti. 19-35 [doi]
• Contrastive Positive Mining for Unsupervised 3D Action Representation LearningHaoyuan Zhang, Yonghong Hou, Wenjing Zhang, Wanqing Li 0001. 36-51 [doi]
• Target-Absent Human AttentionZhibo Yang, Sounak Mondal, Seoyoung Ahn, Gregory J. Zelinsky, Minh Hoai, Dimitris Samaras. 52-68 [doi]
• Uncertainty-Based Spatial-Temporal Attention for Online Action DetectionHongji Guo, Zhou Ren, Yi Wu, Gang Hua 0001, Qiang Ji. 69-86 [doi]
• Iwin: Human-Object Interaction Detection via Transformer with Irregular WindowsDanyang Tu, Xiongkuo Min, Huiyu Duan, Guodong Guo, Guangtao Zhai, Wei Shen 0002. 87-103 [doi]
• Rethinking Zero-shot Action Recognition: Learning from Latent Atomic ActionsYijun Qian, Lijun Yu, Wenhe Liu, Alexander G. Hauptmann. 104-120 [doi]
• Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI DetectionXiaoqian Wu, Yong-Lu Li, Xinpeng Liu, Junyi Zhang, Yuzhe Wu, Cewu Lu. 121-136 [doi]
• Collaborating Domain-Shared and Target-Specific Feature Clustering for Cross-domain 3D Action RecognitionQinying Liu, Zilei Wang. 137-155 [doi]
• Is Appearance Free Action Recognition Possible?Filip Ilic, Thomas Pock, Richard P. Wildes. 156-173 [doi]
• Learning Spatial-Preserved Skeleton Representations for Few-Shot Action RecognitionNing Ma, Hongyi Zhang, Xuhui Li, Sheng Zhou 0004, Zhen Zhang 0023, Jun Wen, Haifeng Li, Jingjun Gu, Jiajun Bu. 174-191 [doi]
• Dual-Evidential Learning for Weakly-supervised Temporal Action LocalizationMengyuan Chen, Junyu Gao, Shicai Yang, Changsheng Xu. 192-208 [doi]
• Global-Local Motion Transformer for Unsupervised Skeleton-Based Action LearningBoeun Kim, Hyung Jin Chang, Jungho Kim, Jin Young Choi 0002. 209-225 [doi]
• AdaFocusV3: On Unified Spatial-Temporal Dynamic Video RecognitionYulin Wang, Yang Yue, Xinhong Xu, Ali Hassani 0001, Victor Kulikov, Nikita Orlov, Shiji Song, Humphrey Shi, Gao Huang. 226-243 [doi]
• Panoramic Human Activity RecognitionRuize Han, Haomin Yan, Jiacheng Li, Song Wang 0002, Wei Feng 0005. 244-261 [doi]
• Delving into Details: Synopsis-to-Detail Networks for Video RecognitionShuxian Liang, Xu Shen, Jianqiang Huang, Xian-Sheng Hua 0001. 262-278 [doi]
• A Generalized and Robust Framework for Timestamp Supervision in Temporal Action SegmentationRahul Rahaman, Dipika Singhania, Alexandre H. Thiery, Angela Yao. 279-296 [doi]
• Few-Shot Action Recognition with Hierarchical Matching and Contrastive LearningSipeng Zheng, Shizhe Chen, Qin Jin. 297-313 [doi]
• PrivHAR: Recognizing Human Actions from Privacy-Preserving LensCarlos Hinojosa, Miguel Marquez, Henry Arguello, Ehsan Adeli 0001, Li Fei-Fei 0001, Juan Carlos Niebles. 314-332 [doi]
• Scale-Aware Spatio-Temporal Relation Learning for Video Anomaly DetectionGuoqiu Li, Guanxiong Cai, Xingyu Zeng, Rui Zhao. 333-350 [doi]
• Compound Prototype Matching for Few-Shot Action RecognitionYifei Huang, Lijin Yang, Yoichi Sato. 351-368 [doi]
• Continual 3D Convolutional Neural Networks for Real-time Processing of VideosLukas Hedegaard, Alexandros Iosifidis. 369-385 [doi]
• Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action RecognitionTianjiao Li, Lin Geng Foo, Qiuhong Ke, Hossein Rahmani, Anran Wang, Jinghua Wang, Jun Liu 0036. 386-403 [doi]
• Dynamic Local Aggregation Network with Adaptive Clusterer for Anomaly DetectionZhiwei Yang, Peng Wu, Jing Liu 0006, Xiaotao Liu. 404-421 [doi]
• Action Quality Assessment with Temporal Parsing TransformerYang Bai, Desen Zhou, Songyang Zhang, Jian Wang, Errui Ding, Yu Guan, Yang Long 0001, Jingdong Wang 0001. 422-438 [doi]
• Entry-Flipped Transformer for Inference and Prediction of Participant BehaviorBo Hu, Tat-Jen Cham. 439-456 [doi]
• Pairwise Contrastive Learning Network for Action Quality AssessmentMingzhe Li, Hong-Bo Zhang, Qing Lei, Zongwen Fan, Jinghua Liu, Ji-Xiang Du. 457-473 [doi]
• Geometric Features Informed Multi-person Human-Object Interaction Recognition in VideosTanqiu Qiao, Qianhui Men, Frederick W. B. Li, Yoshiki Kubotani, Shigeo Morishima, Hubert P. H. Shum. 474-491 [doi]
• ActionFormer: Localizing Moments of Actions with TransformersChen-Lin Zhang, Jianxin Wu 0001, Yin Li. 492-510 [doi]
• SocialVAE: Human Trajectory Prediction Using Timewise LatentsPei Xu, Jean-Bernard Hayet, Ioannis Karamouzas. 511-528 [doi]
• Shape Matters: Deformable Patch AttackZhaoyu Chen, Bo Li 0115, Shuang Wu 0001, Jianghe Xu, Shouhong Ding, Wenqiang Zhang. 529-548 [doi]
• Frequency Domain Model Augmentation for Adversarial AttackYuyang Long, Qilong Zhang, Boheng Zeng, Lianli Gao, Xianglong Liu 0001, Jian Zhang, Jingkuan Song. 549-566 [doi]
• Prior-Guided Adversarial Initialization for Fast Adversarial TrainingXiaojun Jia, Yong Zhang 0034, Xingxing Wei, Baoyuan Wu, Ke Ma 0001, Jue Wang 0001, Xiaochun Cao. 567-584 [doi]
• Enhanced Accuracy and Robustness via Multi-teacher Adversarial DistillationShiji Zhao, Jie Yu, Zhenlong Sun, Bo Zhang, Xingxing Wei. 585-602 [doi]
• LGV: Boosting Adversarial Example Transferability from Large Geometric VicinityMartin Gubri, Maxime Cordy, Mike Papadakis, Yves Le Traon, Koushik Sen. 603-618 [doi]
• A Large-Scale Multiple-objective Method for Black-box Attack Against Object DetectionSiyuan Liang, Longkang Li, Yanbo Fan, Xiaojun Jia, Jingzhi Li, Baoyuan Wu, Xiaochun Cao. 619-636 [doi]
• GradAuto: Energy-Oriented Attack on Dynamic Neural NetworksJianhong Pan, Qichen Zheng, Zhipeng Fan, Hossein Rahmani, Qiuhong Ke, Jun Liu 0036. 637-653 [doi]
• A Spectral View of Randomized Smoothing Under Common Corruptions: Benchmarking and Improving Certified RobustnessJiachen Sun, Akshay Mehra, Bhavya Kailkhura, Pin-Yu Chen, Dan Hendrycks, Jihun Hamm, Z. Morley Mao. 654-671 [doi]
• Improving Adversarial Robustness of 3D Point Cloud Classification ModelsGuanlin Li, Guowen Xu, Han Qiu 0001, Ruan He, Jiwei Li, Tianwei Zhang 0004. 672-689 [doi]
• Learning Extremely Lightweight and Robust Model with Differentiable Constraints on Sparsity and Condition NumberXian Wei, Yangyu Xu, Yanhui Huang, Hairong Lv, Hai Lan, Mingsong Chen, Xuan Tang. 690-707 [doi]
• RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNNHuy Phan, Cong Shi 0004, Yi Xie 0001, Tianfang Zhang, Zhuohang Li, Tianming Zhao 0001, Jian Liu, Yan Wang, Yingying Chen 0001, Bo Yuan 0001. 708-724 [doi]
• Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative NetworksXiao Yang, Yinpeng Dong, Tianyu Pang, Hang Su 0006, Jun Zhu 0001. 725-742 [doi]