{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:59:58Z","timestamp":1783529998710,"version":"3.55.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0102500"],"award-info":[{"award-number":["2018AAA0102500"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2021.3127040","type":"journal-article","created":{"date-parts":[[2021,11,11]],"date-time":"2021-11-11T20:27:34Z","timestamp":1636662454000},"page":"405-417","source":"Crossref","is-referenced-by-count":48,"title":["Efficient Spatio-Temporal Contrastive Learning for Skeleton-Based 3-D Action Recognition"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3168-5770","authenticated-orcid":false,"given":"Xuehao","family":"Gao","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8687-4427","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2967-1516","authenticated-orcid":false,"given":"Yimeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2584-4026","authenticated-orcid":false,"given":"Maosen","family":"Li","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center and the Shanghai Key Laboratory of Multimedia Processing and Transmissions, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2148-2726","authenticated-orcid":false,"given":"Jin-Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Automation Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7092-0596","authenticated-orcid":false,"given":"Shaoyi","family":"Du","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence and Robotics, Xi&#x2019;an Jiaotong University, Xi&#x2019;an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_32"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3023792"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2908352"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11853"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00965"},{"key":"ref6","first-page":"1262","article-title":"Unsupervised learning of view-invariant action representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2896631"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2990082"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2962304"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2897902"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.82"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2802648"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2978637"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.486"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2017.8026282"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2953325"},{"key":"ref20","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Srivastava","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_5"},{"key":"ref23","first-page":"1","article-title":"Unsupervised representation learning by predicting image rotations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Gidaris","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00413"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref27","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2992962"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.100"},{"key":"ref31","first-page":"766","article-title":"Discriminative unsupervised feature learning with convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Dosovitskiy","year":"2014"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref33","article-title":"Can temporal information help with contrastive self-supervised learning?","author":"Bai","year":"2020"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00105"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.04.023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413548"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10605-2_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00056"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486569"},{"key":"ref47","first-page":"15 509","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bachman","year":"2019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09612062.pdf?arnumber=9612062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:39:53Z","timestamp":1705019993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9612062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3127040","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}