{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T16:23:46Z","timestamp":1778171026198,"version":"3.51.4"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"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":["61976010"],"award-info":[{"award-number":["61976010"]}],"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":["62106011"],"award-info":[{"award-number":["62106011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005024","name":"Beijing Postdoctoral Research Foundation","doi-asserted-by":"publisher","award":["2022-zz-077"],"award-info":[{"award-number":["2022-zz-077"]}],"id":[{"id":"10.13039\/501100005024","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Chaoyang District Postdoctoral Research Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/tcsvt.2022.3228731","type":"journal-article","created":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:45:09Z","timestamp":1670874309000},"page":"2839-2851","source":"Crossref","is-referenced-by-count":16,"title":["Active Spatial Positions Based Hierarchical Relation Inference for Group Activity Recognition"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7209-0215","authenticated-orcid":false,"given":"Lifang","family":"Wu","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, College of Information and Communication Engineering, Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianglong","family":"Lang","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, College of Information and Communication Engineering, Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9119-4677","authenticated-orcid":false,"given":"Ye","family":"Xiang","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, College of Information and Communication Engineering, Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6720-234X","authenticated-orcid":false,"given":"Changwen","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zun","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, College of Information and Communication Engineering, Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2230-5716","authenticated-orcid":false,"given":"Zhuming","family":"Wang","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, College of Information and Communication Engineering, Beijing University of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973301"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16437"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461770"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3193574"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930344"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2918725"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240576"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.365"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01341"},{"key":"ref55","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00738"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00300"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3156634"},{"key":"ref19","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref18","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.783"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978942"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.453"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2928540"},{"key":"ref47","first-page":"331","article-title":"Multi-level sequence GAN for group activity recognition","volume":"11361","author":"gammulle","year":"2018","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107925"},{"key":"ref41","first-page":"2178","article-title":"Ontology-based global and collective motion patterns for event classification in basketball videos","volume":"30","author":"wu","year":"2020","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00106"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.07.003"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240572"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00092"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_11"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413195"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2894161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_44"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00808"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref35","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"28","author":"ren","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00972"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2008.919173"},{"key":"ref31","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"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":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33765-9_14"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.313"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.217"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref68","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2001.958410"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_20"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2979742"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01945"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00239"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00908"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref62","first-page":"10890","article-title":"R-drop: Regularized dropout for neural networks","volume":"34","author":"wu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","first-page":"1","article-title":"Is space-time attention all you need for video understanding?","volume":"2","author":"bertasius","year":"2021","journal-title":"Proc ICML"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10144449\/09982683.pdf?arnumber=9982683","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T18:54:20Z","timestamp":1687805660000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9982683\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":68,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3228731","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6]]}}}