{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T05:52:51Z","timestamp":1778824371857,"version":"3.51.4"},"reference-count":85,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["U20B2069"],"award-info":[{"award-number":["U20B2069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"CCF-Tencent Rhino-Bird Research Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3066775","type":"journal-article","created":{"date-parts":[[2021,3,18]],"date-time":"2021-03-18T19:36:26Z","timestamp":1616096186000},"page":"1515-1528","source":"Crossref","is-referenced-by-count":23,"title":["Spatiotemporal Saliency Representation Learning for Video Action Recognition"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6793-2492","authenticated-orcid":false,"given":"Yongqiang","family":"Kong","sequence":"first","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8001-2703","authenticated-orcid":false,"given":"Yunhong","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3497-5052","authenticated-orcid":false,"given":"Annan","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70711"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2191268"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref4","first-page":"1080","volume-title":"Proc. IEEE Int. Conf. Comput. Vis","author":"Gkioxari","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.367"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref7","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Simonyan","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref10","first-page":"6299","article-title":"Quo vadis","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Carreira","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00054"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2769085"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2712608"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33786-4_7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206525"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366154"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2611485"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2333151"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2936112"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2924417"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2787612"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_44"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00875"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3051099"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00834"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00172"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_39"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6633"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.07.054"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2829605"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2308642"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2460013"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2662005"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2761361"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2940851"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2934350"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2754941"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2885229"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.38"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00342"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00737"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6718"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2905607"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3013162"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00102"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00374"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00318"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2966453"},{"key":"ref58","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3029799"},{"key":"ref60","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Feichtenhofer","year":"2016"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00806"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3025665"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2965434"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref69","first-page":"2264","article-title":"More is less: Learning efficient video representations by big-little network and depthwise temporal aggregation","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Fan","year":"2019"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref72","first-page":"802","article-title":"Convolutional LSTM network: A machine learning approach for precipitation nowcasting","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Shi","year":"2015"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2595324"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6239234"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.487"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/97"},{"key":"ref81","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24673-2_3"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09381645.pdf?arnumber=9381645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:15:00Z","timestamp":1704842100000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9381645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3066775","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}