{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T09:08:17Z","timestamp":1768295297348,"version":"3.49.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"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":["2020YFB1406703"],"award-info":[{"award-number":["2020YFB1406703"]}],"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":["62101524"],"award-info":[{"award-number":["62101524"]}],"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":["U21B2026"],"award-info":[{"award-number":["U21B2026"]}],"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":[[2022,10]]},"DOI":"10.1109\/tcsvt.2022.3169842","type":"journal-article","created":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T19:37:18Z","timestamp":1650656238000},"page":"7120-7132","source":"Crossref","is-referenced-by-count":49,"title":["Attention in Attention: Modeling Context Correlation for Efficient Video Classification"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0695-1566","authenticated-orcid":false,"given":"Yanbin","family":"Hao","sequence":"first","affiliation":[{"name":"CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science and School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4881-9344","authenticated-orcid":false,"given":"Shuo","family":"Wang","sequence":"additional","affiliation":[{"name":"CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science and School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8469-7447","authenticated-orcid":false,"given":"Pei","family":"Cao","sequence":"additional","affiliation":[{"name":"Wuhan Research Institute of Posts and Telecommunications, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7638-9022","authenticated-orcid":false,"given":"Xinjian","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering and the School of Artificial Intelligence, Hefei University of Technology, Hefei Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4246-5386","authenticated-orcid":false,"given":"Tong","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Data Science and the School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinmeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Optical Information and Pattern Recognition, Wuhan Institute of Technology, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8472-7992","authenticated-orcid":false,"given":"Xiangnan","family":"He","sequence":"additional","affiliation":[{"name":"CCCD Key Laboratory of Ministry of Culture and Tourism, School of Data Science and School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2586853"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867286"},{"key":"ref4","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","author":"Hu","year":"2018","journal-title":"arXiv:1810.12348"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref8","article-title":"TAM: Temporal adaptive module for video recognition","author":"Liu","year":"2020","journal-title":"arXiv:2005.06803"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3081761"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2870954"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2923712"},{"key":"ref20","article-title":"V4D:4D convolutional neural networks for video-level representation learning","author":"Zhang","year":"2020","journal-title":"arXiv:2002.07442"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref23","article-title":"SlowFast networks for video recognition","author":"Feichtenhofer","year":"2018","journal-title":"arXiv:1812.03982"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_30"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00318"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3142771"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2896029"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2808685"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2894161"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2923444"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9411997"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413595"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref38","article-title":"On the effectiveness of task granularity for transfer learning","author":"Mahdisoltani","year":"2018","journal-title":"arXiv:1804.09235"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref41","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Damen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_24"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"ref48","article-title":"PAN: Towards fast action recognition via learning persistence of appearance","author":"Zhang","year":"2020","journal-title":"arXiv:2008.03462"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00359"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00558"},{"key":"ref56","article-title":"Region-based non-local operation for video classification","author":"Huang","year":"2020","journal-title":"arXiv:2007.09033"},{"key":"ref57","first-page":"1","article-title":"Attention is all we need: Nailing down object-centric attention for egocentric activity recognition","volume-title":"Proc. BMVC","author":"Sudhakaran"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6907"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9910246\/09762292.pdf?arnumber=9762292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:15:44Z","timestamp":1705958144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9762292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10]]},"references-count":58,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3169842","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10]]}}}