{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T11:34:03Z","timestamp":1766748843435,"version":"3.40.3"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["U1836218","62020106012","62106089"],"award-info":[{"award-number":["U1836218","62020106012","62106089"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2017YFC1601800"],"award-info":[{"award-number":["2017YFC1601800"]}]},{"name":"111 Project of Ministry of Education of China","award":["B12018"],"award-info":[{"award-number":["B12018"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2022.3211423","type":"journal-article","created":{"date-parts":[[2022,10,3]],"date-time":"2022-10-03T20:17:21Z","timestamp":1664828241000},"page":"1665-1676","source":"Crossref","is-referenced-by-count":4,"title":["I Know How You Move: Explicit Motion Estimation for Human Action Recognition"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6701-1965","authenticated-orcid":false,"given":"Zhongwei","family":"Shen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-5778","authenticated-orcid":false,"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4550-7879","authenticated-orcid":false,"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9015-3128","authenticated-orcid":false,"given":"Tianyang","family":"Xu","sequence":"additional","affiliation":[{"name":"Centre for Vision, Speech and Signal Processing, University of Surrey, Guildford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2943204"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2866370"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2018.08.014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3448981"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01435-1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050073"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.622"},{"article-title":"The kinetics human action video dataset","year":"2017","author":"Kay","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00154"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00137"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029425"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00558"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00044"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00193"},{"article-title":"Ean: Event adaptive network for enhanced action recognition","year":"2021","author":"Tian","key":"ref18"},{"issue":"1","key":"ref19","first-page":"60","article-title":"Dense trajectories and motion boundary descriptors for action recognition","volume-title":"Int. J. Comput. Vis.","volume":"103","author":"Wang","year":"2013"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2599174"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"article-title":"Convnet architecture search for spatiotemporal feature learning","year":"2017","author":"Tran","key":"ref25"},{"key":"ref26","first-page":"6299","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Carreira","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01233"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00117"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_43"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00054"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00333"},{"article-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning","year":"2022","author":"Li","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref44","first-page":"18","article-title":"Optimization planning for 3d convnets","volume-title":"Proc. 38th Int. Conf. Mach. Learn., Virtual Conf.","author":"Qiu","year":"2021"},{"article-title":"Coca: Contrastive captioners are image-text foundation models","year":"2022","author":"Yu","key":"ref45"},{"article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","year":"2022","author":"Tong","key":"ref46"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref48","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Simonyan","year":"2014"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00151"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350876"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00319"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2887342"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctvcm4g18.8"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01345"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_17"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00561"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10844992\/09907887.pdf?arnumber=9907887","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,7]],"date-time":"2025-04-07T21:56:05Z","timestamp":1744062965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9907887\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3211423","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}