{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T16:44:21Z","timestamp":1777567461983,"version":"3.51.4"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122058"],"award-info":[{"award-number":["62122058"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171317"],"award-info":[{"award-number":["62171317"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019539","name":"Science Fund for Distinguished Young Scholars of Tianjin Municipality","doi-asserted-by":"publisher","award":["22JCJQJC00040"],"award-info":[{"award-number":["22JCJQJC00040"]}],"id":[{"id":"10.13039\/501100019539","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":[[2024,5]]},"DOI":"10.1109\/tcsvt.2023.3324868","type":"journal-article","created":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T18:31:36Z","timestamp":1697481096000},"page":"3919-3929","source":"Crossref","is-referenced-by-count":4,"title":["Toward Grouping in Large Scenes With Occlusion-Aware Spatio\u2013Temporal Transformers"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9619-5030","authenticated-orcid":false,"given":"Jinsong","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingfeng","family":"Gu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-5680","authenticated-orcid":false,"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueyang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2326-0166","authenticated-orcid":false,"given":"Kun","family":"Li","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2355711"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2589859"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014869"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3056684"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00101"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3021409"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2009.5457461"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930344"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.870735"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0123783"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat9891"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-014-0251-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.mlwa.2021.100023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_9"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479963"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.23"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/HRI.2019.8673233"},{"key":"ref19","volume-title":"Conducting Interaction: Patterns of Behavior in Focused Encounters","volume":"7","author":"Kendon","year":"1990"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_11"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0168-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.176"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00333"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref26","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Shi"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070525"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.09.012"},{"key":"ref29","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018","journal-title":"arXiv:1806.01261"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3392824"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1878039.1878048"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00471"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00513"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3246174"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12191"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12068"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1049\/cit2.12145"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2907324"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223955"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233069"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250646"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3240472"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.423"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6699"},{"key":"ref49","article-title":"Decoupled spatial-temporal transformer for video inpainting","author":"Liu","year":"2021","journal-title":"arXiv:2104.06637"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01692"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2022.3202240"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14148"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2929005"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5555\/2980539.2980649"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_35"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref60","article-title":"JRDB-act: A large-scale dataset for spatio-temporal action, social group and activity detection","author":"Ehsanpour","year":"2021","journal-title":"arXiv:2106.08827"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_28"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10527423\/10286297.pdf?arnumber=10286297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T17:35:19Z","timestamp":1715362519000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10286297\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":61,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3324868","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}