{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:56:15Z","timestamp":1784181375584,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"The National Key R&D Program of China","award":["No. 2022ZD0117103"],"award-info":[{"award-number":["No. 2022ZD0117103"]}]},{"name":"The Teaching Reform Project of Shaanxi Higher Continuing Education","award":["No. 21XJZ004"],"award-info":[{"award-number":["No. 21XJZ004"]}]},{"name":"The National Natural Science Foundations of China","award":["No. 62272364"],"award-info":[{"award-number":["No. 62272364"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611900","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"2211-2220","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":59,"title":["Skeleton MixFormer: Multivariate Topology Representation for Skeleton-based Action Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0849-6093","authenticated-orcid":false,"given":"Wentian","family":"Xin","sequence":"first","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2872-388X","authenticated-orcid":false,"given":"Qiguang","family":"Miao","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7044-9514","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6882-9566","authenticated-orcid":false,"given":"Ruyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1788-3746","authenticated-orcid":false,"given":"Chi-Man","family":"Pun","sequence":"additional","affiliation":[{"name":"University of Macau, Macau, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8530-2005","authenticated-orcid":false,"given":"Cheng","family":"Shi","sequence":"additional","affiliation":[{"name":"Xi'an University of Technology, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00333"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859781"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_32"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"e_1_3_2_2_6_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20186--20196","author":"Ha Myoung Hoon","year":"2022","unstructured":"Hyung-gun Chi, Myoung Hoon Ha, Seunggeun Chi, Sang Wan Lee, Qixing Huang, and Karthik Ramani. 2022. Infogcn: Representation learning for human skeleton-based action recognition. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20186--20196."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01324"},{"key":"e_1_3_2_2_8_1","volume-title":"Channel attention and multi-scale graph neural networks for skeleton-based action recognition. AI Communications Preprint","author":"Dang Ronghao","year":"2022","unstructured":"Ronghao Dang, Chengju Liu, Ming Liu, and Qijun Chen. 2022. Channel attention and multi-scale graph neural networks for skeleton-based action recognition. AI Communications Preprint (2022), 1--19."},{"key":"e_1_3_2_2_9_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_10_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, et al. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548546"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the Asian Conference on Computer Vision. 382--398","author":"Gao Zhimin","year":"2022","unstructured":"Zhimin Gao, Peitao Wang, Pei Lv, Xiaoheng Jiang, Qidong Liu, Pichao Wang, Mingliang Xu, and Wanqing Li. 2022. Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition. In Proceedings of the Asian Conference on Computer Vision. 382--398."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548210"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00224"},{"key":"e_1_3_2_2_17_1","volume-title":"Tanzila Saba, Usman Habib, Junaid Ali Khan, and Aaqif Afzaal Abbasi.","author":"Khan Muhammad Attique","year":"2020","unstructured":"Muhammad Attique Khan, Kashif Javed, Sajid Ali Khan, Tanzila Saba, Usman Habib, Junaid Ali Khan, and Aaqif Afzaal Abbasi. 2020. Human action recognition using fusion of multiview and deep features: an application to video surveillance. Multimedia tools and applications (2020), 1--27."},{"key":"e_1_3_2_2_18_1","volume-title":"Hierarchically decomposed graph convolutional networks for skeleton-based action recognition. arXiv preprint arXiv:2208.10741","author":"Lee Jungho","year":"2022","unstructured":"Jungho Lee, Minhyeok Lee, Dogyoon Lee, and Sangyoon Lee. 2022. Hierarchically decomposed graph convolutional networks for skeleton-based action recognition. arXiv preprint arXiv:2208.10741 (2022)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00386"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"e_1_3_2_2_21_1","volume-title":"TranSkeleton: Hierarchical Spatial-Temporal Transformer for Skeleton-Based Action Recognition","author":"Liu Haowei","year":"2023","unstructured":"Haowei Liu, Yongcheng Liu, Yuxin Chen, Chunfeng Yuan, Bing Li, and Weiming Hu. 2023. TranSkeleton: Hierarchical Spatial-Temporal Transformer for Skeleton-Based Action Recognition. IEEE Transactions on Circuits and Systems for Video Technology (2023)."},{"key":"e_1_3_2_2_22_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, Vol. 42, 10 (2019), 2684--2701."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108146"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60639-8_40"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108487"},{"key":"e_1_3_2_2_26_1","volume-title":"Tel Aviv","author":"Pang Yunsheng","year":"2022","unstructured":"Yunsheng Pang, Qiuhong Ke, Hossein Rahmani, James Bailey, and Jun Liu. 2022. IGFormer: Interaction Graph Transformer for Skeleton-based Human Interaction Recognition. In Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23-27, 2022, Proceedings, Part XXV. Springer, 605--622."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68796-0_50"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3028207"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157033"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"e_1_3_2_2_33_1","volume-title":"Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems","author":"Tolstikhin Ilya O","year":"2021","unstructured":"Ilya O Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, et al. 2021. Mlp-mixer: An all-mlp architecture for vision. Advances in neural information processing systems, Vol. 34 (2021), 24261--24272."},{"key":"e_1_3_2_2_34_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2019.03.011"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547811"},{"key":"e_1_3_2_2_38_1","volume-title":"Transformer for Skeleton-based action recognition: A review of recent advances. Neurocomputing","author":"Xin Wentian","year":"2023","unstructured":"Wentian Xin, Ruyi Liu, Yi Liu, Yu Chen, Wenxin Yu, and Qiguang Miao. 2023. Transformer for Skeleton-based action recognition: A review of recent advances. Neurocomputing (2023)."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_2_2_40_1","volume-title":"Unik: A unified framework for real-world skeleton-based action recognition. arXiv preprint arXiv:2107.08580","author":"Yang Di","year":"2021","unstructured":"Di Yang, Yaohui Wang, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca, and Francois Bremond. 2021. Unik: A unified framework for real-world skeleton-based action recognition. arXiv preprint arXiv:2107.08580 (2021)."},{"key":"e_1_3_2_2_41_1","volume-title":"MKE-GCN: Multi-Modal Knowledge Embedded Graph Convolutional Network for Skeleton-Based Action Recognition in the Wild. In 2022 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 01--06","author":"Yang Sen","year":"2022","unstructured":"Sen Yang, Xuanhan Wang, Lianli Gao, and Jingkuan Song. 2022. MKE-GCN: Multi-Modal Knowledge Embedded Graph Convolutional Network for Skeleton-Based Action Recognition in the Wild. In 2022 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 01--06."},{"key":"e_1_3_2_2_42_1","first-page":"28877","article-title":"Do transformers really perform badly for graph representation","volume":"34","author":"Ying Chengxuan","year":"2021","unstructured":"Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, and Tie-Yan Liu. 2021. Do transformers really perform badly for graph representation? Advances in Neural Information Processing Systems, Vol. 34 (2021), 28877--28888.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3253048"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475473"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01022"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611900","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:11:55Z","timestamp":1755821515000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611900"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":46,"alternative-id":["10.1145\/3581783.3611900","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611900","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}