{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:59:59Z","timestamp":1783529999651,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":64,"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":"Young Elite Scientists Sponsorship Program by CAST","award":["2022QNRC001"],"award-info":[{"award-number":["2022QNRC001"]}]},{"name":"Fundamental Research Funds for the Provincial Universities of Zhejiang"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976188, 62272435, U22A2094"],"award-info":[{"award-number":["61976188, 62272435, U22A2094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Pioneer and Leading Goose R&D Program of Zhejiang","award":["2023C01212"],"award-info":[{"award-number":["2023C01212"]}]},{"name":"open research fund of The State Key Laboratory of Multimodal Artificial Intelligence Systems"},{"name":"Public Welfare Technology Research Project of Zhejiang Province","award":["LGF21F020010"],"award-info":[{"award-number":["LGF21F020010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612449","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"2973-2984","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":35,"title":["Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1400-5012","authenticated-orcid":false,"given":"Shengkai","family":"Sun","sequence":"first","affiliation":[{"name":"Zhejiang Gongshang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8179-4508","authenticated-orcid":false,"given":"Daizong","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5244-3274","authenticated-orcid":false,"given":"Jianfeng","family":"Dong","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University & Zhejiang Key Lab of E-Commerce, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4907-3978","authenticated-orcid":false,"given":"Xiaoye","family":"Qu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8105-5497","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-1638","authenticated-orcid":false,"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5566-4689","authenticated-orcid":false,"given":"Xun","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang Gongshang University & Zhejiang Key Lab of E-Commerce, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning. In International Conference on Learning Representations. 1--1.","author":"Bardes Adrien","year":"2022","unstructured":"Adrien Bardes, Jean Ponce, and Yann Lecun. 2022. VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning. In International Conference on Learning Representations. 1--1."},{"key":"e_1_3_2_1_2_1","first-page":"26561","article-title":"Artistic style transfer with internal-external learning and contrastive learning","volume":"34","author":"Chen Haibo","year":"2021","unstructured":"Haibo Chen, Zhizhong Wang, Huiming Zhang, Zhiwen Zuo, Ailin Li, Wei Xing, Dongming Lu, et al. 2021. Artistic style transfer with internal-external learning and contrastive learning. Advances in Neural Information Processing Systems, Vol. 34 (2021), 26561--26573.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Machine Learning. 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International Conference on Machine Learning. 1597--1607."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428459"},{"key":"e_1_3_2_1_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_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591690"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25127"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_13"},{"key":"e_1_3_2_1_14_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00160"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3587251"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475540"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413548"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238514"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547782"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01108"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3418212"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01024"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_42"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_7"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414053"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.04.023"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325056"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00810"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_3"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413802"},{"key":"e_1_3_2_1_39_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475248"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01308"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1214\/009053607000000505"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475218"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475307"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_14"},{"key":"e_1_3_2_1_48_1","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten Laurens","year":"2008","unstructured":"Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing Data using t-SNE. Journal of Machine Learning Research, Vol. 9 (2008), 2579--2605.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109483"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_27"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401151"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413610"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_3"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25451"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475473"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00578"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11853"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544493"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25495"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25502"}],"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\/3581783.3612449","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612449","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:06:36Z","timestamp":1755821196000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612449"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":64,"alternative-id":["10.1145\/3581783.3612449","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612449","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"}}]}}