{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T07:21:24Z","timestamp":1776064884876,"version":"3.50.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFA0713503"],"award-info":[{"award-number":["2020YFA0713503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61773330"],"award-info":[{"award-number":["61773330"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postgraduate Research Innovation Project of Hunan Province","award":["CX20220652"],"award-info":[{"award-number":["CX20220652"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/tcsvt.2022.3233069","type":"journal-article","created":{"date-parts":[[2022,12,29]],"date-time":"2022-12-29T18:42:38Z","timestamp":1672339358000},"page":"3383-3397","source":"Crossref","is-referenced-by-count":32,"title":["MLST-Former: Multi-Level Spatial-Temporal Transformer for Group Activity Recognition"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5834-5699","authenticated-orcid":false,"given":"Xiaolin","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Mathematics and Computational Science, Xiangtan University, Xiangtan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2372-4947","authenticated-orcid":false,"given":"Yan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Mathematics and Computational Science, Xiangtan University, Xiangtan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6892-2218","authenticated-orcid":false,"given":"Dongli","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Automation and Electronics Information, Xiangtan University, Xiangtan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9163-2761","authenticated-orcid":false,"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia"}]},{"given":"Rui","family":"Su","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2012.6467458"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413195"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1889681.1889686"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16437"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.870735"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050918"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2226526"},{"key":"ref58","article-title":"Pose is all you need: The pose only group activity recognition system (POGARS)","author":"thilakarathne","year":"2021","journal-title":"arXiv 2108 04186"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547825"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892494"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_13"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00808"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00457"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_14"},{"key":"ref16","first-page":"1282","article-title":"What are they doing?: Collective activity classification using spatio-temporal relationship among people","author":"choi","year":"2009","journal-title":"Proc IEEE 12th Int Conf Comput Vis Workshops (ICCV Workshops)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727387"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-020-1258-8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.03.066"},{"key":"ref50","article-title":"A multi-stream convolutional neural network framework for group activity recognition","author":"mokhtarzadeh azar","year":"2018","journal-title":"arXiv 1812 10328"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01945"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.221"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.228"},{"key":"ref42","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"ref49","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"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2894161"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3142771"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3049156"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00300"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.217"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973301"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461770"},{"key":"ref34","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":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref36","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref31","first-page":"331","article-title":"Multi-level sequence GAN for group activity recognition","author":"gammulle","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_16"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942030"},{"key":"ref74","first-page":"4997","article-title":"Learning semantics-preserving attention and contextual interaction for group activity recognition","volume":"28","author":"tang","year":"2019","journal-title":"IEEE Access"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2019.02.012"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3085567"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.060"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.313"},{"key":"ref2","first-page":"1","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"simonyan","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3137023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3444685.3446255"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00738"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3056502"},{"key":"ref70","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995707"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240572"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.783"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930344"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.453"},{"key":"ref67","article-title":"Spatial–temporal transformer networks for traffic flow forecasting","author":"xu","year":"2020","journal-title":"arXiv 2001 02908"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.516"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929684"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.70"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01028"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3193574"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-343"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3176064"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978942"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00180"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2918725"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428377"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_15"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10170754\/10003254.pdf?arnumber=10003254","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,17]],"date-time":"2023-07-17T17:55:32Z","timestamp":1689616532000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10003254\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":77,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3233069","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}