{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:05:18Z","timestamp":1781280318971,"version":"3.54.1"},"reference-count":69,"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":[{"name":"National Key R&D Program of China","award":["2018YFB1004300"],"award-info":[{"award-number":["2018YFB1004300"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3050058","type":"journal-article","created":{"date-parts":[[2021,1,9]],"date-time":"2021-01-09T19:51:19Z","timestamp":1610221879000},"page":"313-322","source":"Crossref","is-referenced-by-count":9,"title":["SAM: Modeling Scene, Object and Action With Semantics Attention Modules for Video Recognition"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1721-035X","authenticated-orcid":false,"given":"Xing","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8689-5807","authenticated-orcid":false,"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref38","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2234731"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"},{"key":"ref30","first-page":"399","article-title":"Videos as space-time region graphs","author":"wang","year":"0","journal-title":"Proc ECCV"},{"key":"ref37","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.109"},{"key":"ref35","first-page":"3021","article-title":"Robust late fusion with rank minimization","author":"ye","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref62","first-page":"20","article-title":"Temporal segment networks: Towards good practices for deep action recognition","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_18"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00632"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3007826"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2129870"},{"key":"ref67","first-page":"122","article-title":"Multi-modal domain adaptation for fine-grained action recognition","author":"munro","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-018-9801-4"},{"key":"ref69","first-page":"1111","article-title":"Temporal reasoning in videos using convolutional gated recurrent units","author":"dwibedi","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.86"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref20","article-title":"YouTube-8 M: A large-scale video classification benchmark","author":"abu-el-haija","year":"2016","journal-title":"arXiv 1609 08675"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00034"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref25","first-page":"6299","author":"carreira","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00189"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00440"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref55","article-title":"The kinetics human action video dataset","author":"kay","year":"0","journal-title":"arXiv 1705 06950"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01019"},{"key":"ref53","first-page":"34","article-title":"Attentional pooling for action recognition","author":"girdhar","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref52","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.11212","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"song","year":"2017","journal-title":"AAAI"},{"key":"ref10","first-page":"46","author":"jain","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.476"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.12"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.339"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_39"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301333"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref16","article-title":"Learnable pooling with context gating for video classification","author":"miech","year":"2017","journal-title":"CVPR Workshop"},{"key":"ref17","first-page":"2528","article-title":"Multimodal attention for fusion of audio and spatiotemporal features for video description","author":"hori","year":"0","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.337"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2829163"},{"key":"ref3","article-title":"Untrimmed video classification for activity detection: Submission to activitynet challenge","author":"singh","year":"2016","journal-title":"CVPR Workshop"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2848543"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"ref8","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume":"27","author":"simonyan","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019030"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/227"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2888822"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"1347","DOI":"10.1109\/TIP.2017.2778563","article-title":"Recurrent spatial-temporal attention network for action recognition in videos","volume":"27","author":"du","year":"2017","journal-title":"IEEE Trans Image Process"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.332"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref41","article-title":"Adaptive co-attention network for named entity recognition in tweets","volume":"32","author":"zhang","year":"0","journal-title":"Proc Assoc Adv Artif Intell"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2904878"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2729019"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09316975.pdf?arnumber=9316975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T03:13:40Z","timestamp":1670728420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9316975\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3050058","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}