{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T18:19:00Z","timestamp":1771265940933,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Chinese National Science & Technology Pillar Program","award":["No. 2022YFC2009900\/2022YFC2009903"],"award-info":[{"award-number":["No. 2022YFC2009900\/2022YFC2009903"]}]},{"name":"the National Natural Science Foundation of China","award":["No. 62122018, No. 62020106008, No. 61772116, No. 61872064"],"award-info":[{"award-number":["No. 62122018, No. 62020106008, No. 61772116, No. 61872064"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3547811","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:42:35Z","timestamp":1665416555000},"page":"1670-1678","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":27,"title":["Skeleton-based Action Recognition via Adaptive Cross-Form Learning"],"prefix":"10.1145","author":[{"given":"Xuanhan","family":"Wang","sequence":"first","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Dai","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lianli","family":"Gao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China & Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Yuxin Chen Ziqi Zhang Chunfeng Yuan Bing Li Ying Deng and Weiming Hu. 2021. Channel-wise topology refinement graph convolution for skeleton-based action recognition. In ICCV. Yuxin Chen Ziqi Zhang Chunfeng Yuan Bing Li Ying Deng and Weiming Hu. 2021. Channel-wise topology refinement graph convolution for skeleton-based action recognition. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Ke Cheng Yifan Zhang Congqi Cao Lei Shi Jian Cheng and Hanqing Lu. 2020a. Decoupling gcn with dropgraph module for skeleton-based action recognition. In ECCV. Ke Cheng Yifan Zhang Congqi Cao Lei Shi Jian Cheng and Hanqing Lu. 2020a. Decoupling gcn with dropgraph module for skeleton-based action recognition. In ECCV.","DOI":"10.1007\/978-3-030-58586-0_32"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Ke Cheng Yifan Zhang Xiangyu He Weihan Chen Jian Cheng and Hanqing Lu. 2020b. Skeleton-based action recognition with shift graph convolutional network. In CVPR. Ke Cheng Yifan Zhang Xiangyu He Weihan Chen Jian Cheng and Hanqing Lu. 2020b. Skeleton-based action recognition with shift graph convolutional network. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"e_1_3_2_1_4_1","volume-title":"Revisiting Skeleton-based Action Recognition. arXiv preprint arXiv:2104.13586","author":"Duan Haodong","year":"2021","unstructured":"Haodong Duan , Yue Zhao , Kai Chen , Dian Shao , Dahua Lin , and Bo Dai . 2021. Revisiting Skeleton-based Action Recognition. arXiv preprint arXiv:2104.13586 ( 2021 ). Haodong Duan, Yue Zhao, Kai Chen, Dian Shao, Dahua Lin, and Bo Dai. 2021. Revisiting Skeleton-based Action Recognition. arXiv preprint arXiv:2104.13586 (2021)."},{"key":"e_1_3_2_1_5_1","volume-title":"Play and rewind: Context-aware video temporal action proposals. Pattern Recognition","author":"Gao Lianli","year":"2020","unstructured":"Lianli Gao , Tao Li , Jingkuan Song , Zhou Zhao , and Heng Tao Shen . 2020. Play and rewind: Context-aware video temporal action proposals. Pattern Recognition ( 2020 ), 107477. Lianli Gao, Tao Li, Jingkuan Song, Zhou Zhao, and Heng Tao Shen. 2020. Play and rewind: Context-aware video temporal action proposals. Pattern Recognition (2020), 107477."},{"key":"e_1_3_2_1_6_1","unstructured":"Qiushan Guo Xinjiang Wang Yichao Wu Zhipeng Yu Ding Liang Xiaolin Hu and Ping Luo. 2020. Online Knowledge Distillation via Collaborative Learning. In CVPR. 11017--11026. Qiushan Guo Xinjiang Wang Yichao Wu Zhipeng Yu Ding Liang Xiaolin Hu and Ping Luo. 2020. Online Knowledge Distillation via Collaborative Learning. In CVPR. 11017--11026."},{"key":"e_1_3_2_1_7_1","unstructured":"Maosen Li Siheng Chen Xu Chen Ya Zhang Yanfeng Wang and Qi Tian. 2019. Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition. In CVPR. 3595--3603. Maosen Li Siheng Chen Xu Chen Ya Zhang Yanfeng Wang and Qi Tian. 2019. Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition. In CVPR. 3595--3603."},{"key":"e_1_3_2_1_8_1","volume-title":"Hard-net: Hardness-aware discrimination network for 3d early activity prediction. In ECCV.","author":"Li Tianjiao","year":"2020","unstructured":"Tianjiao Li , Jun Liu , Wei Zhang , and Lingyu Duan . 2020 . Hard-net: Hardness-aware discrimination network for 3d early activity prediction. In ECCV. Tianjiao Li, Jun Liu, Wei Zhang, and Lingyu Duan. 2020. Hard-net: Hardness-aware discrimination network for 3d early activity prediction. In ECCV."},{"key":"e_1_3_2_1_9_1","unstructured":"Tianjiao Li Jun Liu Wei Zhang Yun Ni Wenqian Wang and Zhiheng Li. 2021. UAV-Human: A Large Benchmark for Human Behavior Understanding With Unmanned Aerial Vehicles. In CVPR. Tianjiao Li Jun Liu Wei Zhang Yun Ni Wenqian Wang and Zhiheng Li. 2021. UAV-Human: A Large Benchmark for Human Behavior Understanding With Unmanned Aerial Vehicles. In CVPR."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Yuen-Jen Lin Hsuan-Kai Kao Yih-Chih Tseng Ming Tsai and Li Su. 2020. A Human-Computer Duet System for Music Performance. In ACM MM. 772--780. Yuen-Jen Lin Hsuan-Kai Kao Yih-Chih Tseng Ming Tsai and Li Su. 2020. A Human-Computer Duet System for Music Performance. In ACM MM. 772--780.","DOI":"10.1145\/3394171.3413921"},{"key":"e_1_3_2_1_11_1","volume-title":"Ntu rgb d 120: A large-scale benchmark for 3d human activity understanding","author":"Liu Jun","year":"2019","unstructured":"Jun Liu , Amir Shahroudy , Mauricio Perez , Gang Wang , Ling-Yu Duan , and Alex C Kot . 2019. Ntu rgb d 120: A large-scale benchmark for 3d human activity understanding . IEEE Transactions on Pattern Analysis and Machine Intelligence ( 2019 ). Jun Liu, Amir Shahroudy, Mauricio Perez, Gang Wang, Ling-Yu Duan, and Alex C Kot. 2019. Ntu rgb d 120: A large-scale benchmark for 3d human activity understanding. IEEE Transactions on Pattern Analysis and Machine Intelligence (2019)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Jun Liu Gang Wang Ping Hu Ling-Yu Duan and Alex C Kot. 2017. Global context-aware attention lstm networks for 3d action recognition. In CVPR. Jun Liu Gang Wang Ping Hu Ling-Yu Duan and Alex C Kot. 2017. Global context-aware attention lstm networks for 3d action recognition. In CVPR.","DOI":"10.1109\/CVPR.2017.391"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Kun Liu and Huadong Ma. 2019. Exploring Background-bias for Anomaly Detection in Surveillance Videos. In ACM MM. 1490--1499. Kun Liu and Huadong Ma. 2019. Exploring Background-bias for Anomaly Detection in Surveillance Videos. In ACM MM. 1490--1499.","DOI":"10.1145\/3343031.3350998"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Ziyu Liu Hongwen Zhang Zhenghao Chen Zhiyong Wang and Wanli Ouyang. 2020. Disentangling and unifying graph convolutions for skeleton-based action recognition. In CVPR. Ziyu Liu Hongwen Zhang Zhenghao Chen Zhiyong Wang and Wanli Ouyang. 2020. Disentangling and unifying graph convolutions for skeleton-based action recognition. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Wei Peng Jingang Shi Zhaoqiang Xia and Guoying Zhao. 2020. Mix Dimension in Poincar\u00e9 Geometry for 3D Skeleton-based Action Recognition. In ACM MM. 1432--1440. Wei Peng Jingang Shi Zhaoqiang Xia and Guoying Zhao. 2020. Mix Dimension in Poincar\u00e9 Geometry for 3D Skeleton-based Action Recognition. In ACM MM. 1432--1440.","DOI":"10.1145\/3394171.3413910"},{"key":"e_1_3_2_1_16_1","volume-title":"Ryoo","author":"Piergiovanni A. J.","year":"2019","unstructured":"A. J. Piergiovanni and Michael S . Ryoo . 2019 . Representation Flow for Action Recognition. In CVPR. 9945--9953. A. J. Piergiovanni and Michael S. Ryoo. 2019. Representation Flow for Action Recognition. In CVPR. 9945--9953."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Amir Shahroudy Jun Liu Tian-Tsong Ng and Gang Wang. 2016. Ntu rgb d: A large scale dataset for 3d human activity analysis. In CVPR. Amir Shahroudy Jun Liu Tian-Tsong Ng and Gang Wang. 2016. Ntu rgb d: A large scale dataset for 3d human activity analysis. In CVPR.","DOI":"10.1109\/CVPR.2016.115"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Lei Shi Yifan Zhang Jian Cheng and Hanqing Lu. 2019a. Skeleton-based action recognition with directed graph neural networks. In CVPR. Lei Shi Yifan Zhang Jian Cheng and Hanqing Lu. 2019a. Skeleton-based action recognition with directed graph neural networks. In CVPR.","DOI":"10.1109\/CVPR.2019.00810"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Lei Shi Yifan Zhang Jian Cheng and Hanqing Lu. 2019b. Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In CVPR. Lei Shi Yifan Zhang Jian Cheng and Hanqing Lu. 2019b. Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In CVPR.","DOI":"10.1109\/CVPR.2019.01230"},{"key":"e_1_3_2_1_20_1","unstructured":"Chenyang Si Wentao Chen Wei Wang Liang Wang and Tieniu Tan. 2019. An attention enhanced graph convolutional lstm network for skeleton-based action recognition. In CVPR. Chenyang Si Wentao Chen Wei Wang Liang Wang and Tieniu Tan. 2019. An attention enhanced graph convolutional lstm network for skeleton-based action recognition. In CVPR."},{"key":"e_1_3_2_1_21_1","unstructured":"Chenyang Si Ya Jing Wei Wang Liang Wang and Tieniu Tan. 2018. Skeleton-based action recognition with spatial reasoning and temporal stack learning. In ECCV. Chenyang Si Ya Jing Wei Wang Liang Wang and Tieniu Tan. 2018. Skeleton-based action recognition with spatial reasoning and temporal stack learning. In ECCV."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Yi-Fan Song Zhang Zhang Caifeng Shan and Liang Wang. 2020. Stronger faster and more explainable: A graph convolutional baseline for skeleton-based action recognition. In ACM MM. Yi-Fan Song Zhang Zhang Caifeng Shan and Liang Wang. 2020. Stronger faster and more explainable: A graph convolutional baseline for skeleton-based action recognition. In ACM MM.","DOI":"10.1145\/3394171.3413802"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Ke Sun Bin Xiao Dong Liu and Jingdong Wang. 2019. Deep High-Resolution Representation Learning for Human Pose Estimation. In CVPR. 5693--5703. Ke Sun Bin Xiao Dong Liu and Jingdong Wang. 2019. Deep High-Resolution Representation Learning for Human Pose Estimation. In CVPR. 5693--5703.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_1_24_1","volume-title":"UAV-Satellite View Synthesis for Cross-view Geo-Localization","author":"Tian Xiaoyang","year":"2021","unstructured":"Xiaoyang Tian , Jie Shao , Deqiang Ouyang , and Heng Tao Shen . 2021. UAV-Satellite View Synthesis for Cross-view Geo-Localization . IEEE Transactions on Circuits and Systems for Video Technology ( 2021 ). Xiaoyang Tian, Jie Shao, Deqiang Ouyang, and Heng Tao Shen. 2021. UAV-Satellite View Synthesis for Cross-view Geo-Localization. IEEE Transactions on Circuits and Systems for Video Technology (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition. arXiv preprint arXiv:2202.04075","author":"Tu Zhigang","year":"2022","unstructured":"Zhigang Tu , Jiaxu Zhang , Hongyan Li , Yujin Chen , and Junsong Yuan . 2022. Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition. arXiv preprint arXiv:2202.04075 ( 2022 ). Zhigang Tu, Jiaxu Zhang, Hongyan Li, Yujin Chen, and Junsong Yuan. 2022. Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition. arXiv preprint arXiv:2202.04075 (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3103973"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Limin Wang Yuanjun Xiong Zhe Wang Yu Qiao Dahua Lin Xiaoou Tang and Luc Van Gool. 2016. Temporal Segment Networks: Towards Good Practices for Deep Action Recognition. In ECCV. 20--36. Limin Wang Yuanjun Xiong Zhe Wang Yu Qiao Dahua Lin Xiaoou Tang and Luc Van Gool. 2016. Temporal Segment Networks: Towards Good Practices for Deep Action Recognition. In ECCV. 20--36.","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Xuanhan Wang Lianli Gao Yan Dai Yixuan Zhou and Jingkuan Song. 2021. Semantic-aware Transfer with Instance-adaptive Parsing for Crowded Scenes Pose Estimation. In ACM MM. 686--694. Xuanhan Wang Lianli Gao Yan Dai Yixuan Zhou and Jingkuan Song. 2021. Semantic-aware Transfer with Instance-adaptive Parsing for Crowded Scenes Pose Estimation. In ACM MM. 686--694.","DOI":"10.1145\/3474085.3475233"},{"key":"e_1_3_2_1_29_1","volume-title":"KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences","author":"Wang Xuanhan","year":"2022","unstructured":"Xuanhan Wang , Lianli Gao , Yixuan Zhou , Jingkuan Song , and Meng Wang . 2022 . KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences . IEEE Transactions on Circuits and Systems for Video Technology ( 2022). Xuanhan Wang, Lianli Gao, Yixuan Zhou, Jingkuan Song, and Meng Wang. 2022. KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences. IEEE Transactions on Circuits and Systems for Video Technology (2022)."},{"key":"e_1_3_2_1_30_1","volume-title":"Javen Qinfeng Shi, and Shengyong Chen","author":"Wang Zhenhua","year":"2021","unstructured":"Zhenhua Wang , Jiajun Meng , Dongyan Guo , Jianhua Zhang , Javen Qinfeng Shi, and Shengyong Chen . 2021 b. Consistency-Aware Graph Network for Human Interaction Understanding. In ICCV. Zhenhua Wang, Jiajun Meng, Dongyan Guo, Jianhua Zhang, Javen Qinfeng Shi, and Shengyong Chen. 2021b. Consistency-Aware Graph Network for Human Interaction Understanding. In ICCV."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Liuyu Xiang Guiguang Ding and Jungong Han. 2020. Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification. In ECCV. Liuyu Xiang Guiguang Ding and Jungong Han. 2020. Learning from multiple experts: Self-paced knowledge distillation for long-tailed classification. In ECCV.","DOI":"10.1007\/978-3-030-58558-7_15"},{"key":"e_1_3_2_1_32_1","volume-title":"Kristen Grauman, Jitendra Malik, and Christoph Feichtenhofer.","author":"Xiao Fanyi","year":"2020","unstructured":"Fanyi Xiao , Yong Jae Lee , Kristen Grauman, Jitendra Malik, and Christoph Feichtenhofer. 2020 . Audiovisual SlowFast Networks for Video Recognition . arXiv preprint arXiv:2001.08740 (2020). Fanyi Xiao, Yong Jae Lee, Kristen Grauman, Jitendra Malik, and Christoph Feichtenhofer. 2020. Audiovisual SlowFast Networks for Video Recognition. arXiv preprint arXiv:2001.08740 (2020)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Sijie Yan Yuanjun Xiong and Dahua Lin. 2018. Spatial temporal graph convolutional networks for skeleton-based action recognition. In AAAI. Sijie Yan Yuanjun Xiong and Dahua Lin. 2018. Spatial temporal graph convolutional networks for skeleton-based action recognition. In AAAI.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_2_1_34_1","unstructured":"Fanfan Ye Shiliang Pu Qiaoyong Zhong Chao Li Di Xie and Huiming Tang. 2020. Dynamic GCN: Context-enriched topology learning for skeleton-based action recognition. In ACM MM. Fanfan Ye Shiliang Pu Qiaoyong Zhong Chao Li Di Xie and Huiming Tang. 2020. Dynamic GCN: Context-enriched topology learning for skeleton-based action recognition. In ACM MM."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Pengfei Zhang Cuiling Lan Wenjun Zeng Junliang Xing Jianru Xue and Nanning Zheng. 2020. Semantics-guided neural networks for efficient skeleton-based human action recognition. In CVPR. Pengfei Zhang Cuiling Lan Wenjun Zeng Junliang Xing Jianru Xue and Nanning Zheng. 2020. Semantics-guided neural networks for efficient skeleton-based human action recognition. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"e_1_3_2_1_36_1","unstructured":"Yichen Zhu and Yi Wang. 2021. Student customized knowledge distillation: Bridging the gap between student and teacher. In ICCV. Yichen Zhu and Yi Wang. 2021. Student customized knowledge distillation: Bridging the gap between student and teacher. In ICCV."}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547811","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3547811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:34Z","timestamp":1750186954000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3547811"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":36,"alternative-id":["10.1145\/3503161.3547811","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3547811","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}