{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T04:29:37Z","timestamp":1768883377898,"version":"3.49.0"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62031023"],"award-info":[{"award-number":["62031023"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61801396"],"award-info":[{"award-number":["61801396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3249906","type":"journal-article","created":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T19:04:59Z","timestamp":1677524699000},"page":"5076-5088","source":"Crossref","is-referenced-by-count":12,"title":["Self-Supervised Global Spatio-Temporal Interaction Pre-Training for Group Activity Recognition"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0954-2757","authenticated-orcid":false,"given":"Zexing","family":"Du","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4578-2686","authenticated-orcid":false,"given":"Xue","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3439-0644","authenticated-orcid":false,"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-018-1560-4"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2015.11.013"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547825"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.07.515"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00156"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.aeue.2015.12.016"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547822"},{"key":"ref53","first-page":"1","article-title":"One-shot deep model for end-to-end multi-person activity recognition","author":"tarashima","year":"2021","journal-title":"Proc Brit Mach Vis Conf"},{"key":"ref52","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2015.1061701"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01945"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2577044"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16437"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.220"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.07.425"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.217"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978942"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_5"},{"key":"ref45","article-title":"HiGCIN: Hierarchical graph-based cross inference network for group activity recognition","author":"yan","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00106"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_13"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240572"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2894161"},{"key":"ref85","first-page":"101","article-title":"StagNet: An attentive semantic RNN for group activity recognition","author":"qi","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2280849"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942030"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_22"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973301"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2965299"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.2020-0101"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05018-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106624"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3069376"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3441628"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1504\/IJCVR.2017.084991"},{"key":"ref82","first-page":"1","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2009.5457461"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240576"},{"key":"ref84","first-page":"3791","article-title":"Self-supervised video representation learning by uncovering spatio-temporal statistics","volume":"44","author":"wang","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2010.2057013"},{"key":"ref79","first-page":"14476","article-title":"Look at what i’m doing: Self-supervised spatial grounding of narrations in instructional videos","volume":"34","author":"tan","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2269780"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3175605"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_37"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_14"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00300"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00994"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00186"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16189"},{"key":"ref33","first-page":"4576","article-title":"Joint inference of groups, events and human roles in aerial videos","author":"shu","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref77","article-title":"Multi-granularity anchor-contrastive representation learning for semi-supervised skeleton-based action recognition","author":"shu","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref32","first-page":"1354","article-title":"Social roles in hierarchical models for human activity recognition","author":"lan","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00358"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.365"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.783"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.453"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6840"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018545"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413694"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17274"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2015.08.036"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.607"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0168-3"},{"key":"ref67","first-page":"21271","article-title":"Bootstrap your own latent—A new approach to self-supervised learning","volume":"33","author":"grill","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.79"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_11"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490582"},{"key":"ref63","first-page":"1","article-title":"Decomposing motion and content for natural video sequence prediction","author":"villegas","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00105"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00738"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01575"},{"key":"ref60","first-page":"1","article-title":"Unsupervised learning of disentangled representations from video","volume":"30","author":"denton","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3135117"},{"key":"ref61","first-page":"1","article-title":"PSTNet: Point spatio-temporal convolution on point cloud sequences","author":"fan","year":"2021","journal-title":"Proc Int Conf Learn Represent"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10054465.pdf?arnumber=10054465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:41:54Z","timestamp":1695667314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10054465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":87,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3249906","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}