{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:23:00Z","timestamp":1784737380889,"version":"3.55.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"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":["62306272"],"award-info":[{"award-number":["62306272"]}],"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":["62276237"],"award-info":[{"award-number":["62276237"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC3603102"],"award-info":[{"award-number":["2023YFC3603102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100022963","name":"Pioneer and \u201cLeading Goose\u201d R&D Program of Zhejiang","doi-asserted-by":"publisher","award":["2024C03027"],"award-info":[{"award-number":["2024C03027"]}],"id":[{"id":"10.13039\/100022963","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":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3383477","type":"journal-article","created":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T20:06:11Z","timestamp":1712001971000},"page":"7962-7974","source":"Crossref","is-referenced-by-count":3,"title":["Heterogeneous Graph Network for Action Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0763-3658","authenticated-orcid":false,"given":"Yisheng","family":"Zhao","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6918-4088","authenticated-orcid":false,"given":"Huaiyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2555-343X","authenticated-orcid":false,"given":"Ruohong","family":"Huan","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7560-5990","authenticated-orcid":false,"given":"Yaoqi","family":"Bao","sequence":"additional","affiliation":[{"name":"Hangzhou Institute of Technology, Xidian University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9335-4291","authenticated-orcid":false,"given":"Yun","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00053"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00315"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00801"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00334"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00069"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.396"},{"key":"ref13","article-title":"The AVA-kinetics localized human actions video\n                        dataset","author":"Li","year":"2020","journal-title":"arXiv:2005.00214"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref18","first-page":"35946","article-title":"Masked autoencoders as spatiotemporal\n                        learners","volume-title":"Proc. Adv. Neural Inf. Process.\n                        Syst.","author":"Feichtenhofer"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref20","first-page":"29441","article-title":"Hiera: A hierarchical vision transformer without the\n                        bells-and-whistles","volume-title":"Proc. 40th Int. Conf.\n                        Mach. Learn.","author":"Ryali"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3178957"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132058"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01473-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201186"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3134410"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3058098"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3079900"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467350"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25435"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298301"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313562"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2882192"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207228"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00037"},{"key":"ref39","article-title":"Pose flow: Efficient online pose\n                        tracking","volume":"29","author":"Xiu","year":"2018","journal-title":"arXiv:1802.00977"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref42","article-title":"Graph transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yun"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.472"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00035"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref46","article-title":"The kinetics human action video\n                        dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref47","volume-title":"Detectron","author":"Girshick","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.02.001"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01226"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00015"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10486955.pdf?arnumber=10486955","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T17:52:14Z","timestamp":1743616334000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10486955\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":50,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3383477","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}