{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:22:09Z","timestamp":1792786929898,"version":"4.5.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China Cultural Technology and Modern Service Industry Key Special Project","award":["2021YFF0901700"],"award-info":[{"award-number":["2021YFF0901700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3307933","type":"journal-article","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T14:01:43Z","timestamp":1692799303000},"page":"3207-3220","source":"Crossref","is-referenced-by-count":35,"title":["Learning Representations by Contrastive Spatio-Temporal Clustering for Skeleton-Based Action Recognition"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2907-086X","authenticated-orcid":false,"given":"Mingdao","family":"Wang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueming","family":"Li","sequence":"additional","affiliation":[{"name":"School of Digital Media and Design Arts, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6116-7080","authenticated-orcid":false,"given":"Siqi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3905-2062","authenticated-orcid":false,"given":"Xianlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Digital Media and Design Arts, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Ma","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Alberta, Edmonton, AB, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6327-5023","authenticated-orcid":false,"given":"Yue","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Digital Media and Design Arts, Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183112"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2859620"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.4018\/IJACI.2017100101"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3127040"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3042986"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00123"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3129616"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3132739"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.007"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413548"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11853"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01317"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_7"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.04.023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00471"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19957"},{"key":"ref22","article-title":"Contrastive learning from spatio-temporal mixed skeleton sequences for self-supervised skeleton-based action recognition","author":"Chen","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_42"},{"issue":"86","key":"ref24","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475307"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3207577"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01954"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref30","article-title":"Unsupervised representation learning by predicting image rotations","author":"Gidaris","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6840"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_3"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_11"},{"key":"ref36","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref37","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Khosla","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2937514"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177704014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00654"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_3"},{"key":"ref45","article-title":"Distilling the knowledge in a neural network","author":"Hinton"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_9"},{"key":"ref47","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Caron","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00696"},{"key":"ref49","first-page":"2292","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Cuturi","year":"2013"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.84"},{"key":"ref51","article-title":"Self-labelling via simultaneous clustering and representation learning","author":"Asano","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3086758"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2960588"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990082"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3239751"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10227565.pdf?arnumber=10227565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T08:17:38Z","timestamp":1710404258000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10227565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3307933","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}