{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T01:57:32Z","timestamp":1785808652488,"version":"3.56.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"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":["62206215"],"award-info":[{"award-number":["62206215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Post-Doctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M712537"],"award-info":[{"award-number":["2022M712537"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China National Post-Doctoral Program for Innovative Talents","award":["BX2021241"],"award-info":[{"award-number":["BX2021241"]}]},{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Plan in Shaanxi Province of China","doi-asserted-by":"publisher","award":["2023-JC-JQ-51"],"award-info":[{"award-number":["2023-JC-JQ-51"]}],"id":[{"id":"10.13039\/501100017596","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":[[2024,2]]},"DOI":"10.1109\/tcsvt.2023.3287201","type":"journal-article","created":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:23:28Z","timestamp":1687199008000},"page":"695-708","source":"Crossref","is-referenced-by-count":47,"title":["Dynamic Spatial Focus for Efficient Compressed Video Action Recognition"],"prefix":"10.1109","volume":"34","author":[{"given":"Ziwei","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8379-4915","authenticated-orcid":false,"given":"Le","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3911-8263","authenticated-orcid":false,"given":"Lijun","family":"He","sequence":"additional","affiliation":[{"name":"School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7251-0988","authenticated-orcid":false,"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7566-1634","authenticated-orcid":false,"given":"Fan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2018.8698676"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3087023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref4","article-title":"ConvNet architecture search for spatiotemporal feature learning","author":"Tran","year":"2017","journal-title":"arXiv:1708.05038"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00797"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2976789"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00633"},{"key":"ref11","first-page":"1","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01594"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2791180"},{"key":"ref16","article-title":"Mobile video action recognition","author":"Huo","year":"2019","journal-title":"arXiv:1908.10155"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412213"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413641"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI51738.2020.00017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3024646"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3112008"},{"key":"ref23","first-page":"2432","article-title":"Glance and focus: A dynamic approach to reducing spatial redundancy in image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3125263"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref26","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012","journal-title":"arXiv:1212.0402"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref28","first-page":"1","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Jaderberg"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.194"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_19"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2914137"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref35","article-title":"AdaFuse: Adaptive temporal fusion network for efficient action recognition","author":"Meng","year":"2021","journal-title":"arXiv:2102.05775"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2818151"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2008.927112"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.332"},{"key":"ref42","article-title":"Compressed video action recognition with refined motion vector","author":"Cao","year":"2019","journal-title":"arXiv:1910.02533"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SIBGRAPI.2019.00012"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00561"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3197395"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2133090"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117837"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029425"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00239"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_31"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00189"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3142759"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/148"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref62","article-title":"Flow-distilled IP two-stream networks for compressed video action recognition","author":"Huang","year":"2019","journal-title":"arXiv:1912.04462"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00350"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10422872\/10155270.pdf?arnumber=10155270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T19:11:13Z","timestamp":1708024273000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10155270\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":65,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3287201","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}