{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:18:57Z","timestamp":1784146737167,"version":"3.55.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,11,1]],"date-time":"2020-11-01T00:00:00Z","timestamp":1604188800000},"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":["61872021"],"award-info":[{"award-number":["61872021"]}],"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":["61690202"],"award-info":[{"award-number":["61690202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Nova Program of Science and Technology","award":["Z191100001119050"],"award-info":[{"award-number":["Z191100001119050"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1109\/tmm.2020.2965434","type":"journal-article","created":{"date-parts":[[2020,1,10]],"date-time":"2020-01-10T20:55:53Z","timestamp":1578689753000},"page":"2990-3001","source":"Crossref","is-referenced-by-count":152,"title":["Spatio-Temporal Attention Networks for Action Recognition and Detection"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5009-6536","authenticated-orcid":false,"given":"Jun","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8425-4195","authenticated-orcid":false,"given":"Xianglong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3947-2991","authenticated-orcid":false,"given":"Wenxuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8212-715X","authenticated-orcid":false,"given":"Mingyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2549-8322","authenticated-orcid":false,"given":"Jingkuan","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6597-7248","authenticated-orcid":false,"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref72","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":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00876"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01018"},{"key":"ref76","article-title":"Sap: Self-adaptive proposal model for temporal action detection based on reinforcement learn-ing","author":"huang","year":"0","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref74","article-title":"THUMOS challenge: Action Recognition with a large number of classes","author":"jiang","year":"2014"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.751"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00627"},{"key":"ref33","first-page":"5","article-title":"Fast saliency based pooling of fisher encoded dense trajectories","volume":"1","author":"karaman","year":"0","journal-title":"Proc Eur Conf Comput Vision THUMOS Workshop"},{"key":"ref32","article-title":"The lear submission at thumos 2014","author":"oneata","year":"0","journal-title":"Proc Workshop Eur Conf Comput Vis"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.04.007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref37","first-page":"2","article-title":"Action Recognition and detection by combining motion and appearance features","volume":"1","author":"wang","year":"2014","journal-title":"THUMOS Action Recognition challenge"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.91"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-85729-994-9_4"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.787"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00124"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_5"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00209"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref29","first-page":"5152","article-title":"Temporal gaussian mixture layer for videos","author":"piergiovanni","year":"0","journal-title":"Proceedings 36th Int Conf Mach Learn"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350876"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2907453"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00054"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00155"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref24","article-title":"Action Recognition using visual attention","author":"sharma","year":"2015","journal-title":"CoRR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1080\/135062800394667"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.342"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00015"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2771462"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00817"},{"key":"ref56","first-page":"34","article-title":"Attentional pooling for action Recognition","author":"girdhar","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.683"},{"key":"ref52","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":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00630"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.82"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72393-6_85"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_18"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2866370"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018328"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00807"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00318"},{"key":"ref9","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref46","first-page":"577","article-title":"Attention-based models for speech Recognition","author":"chorowski","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref45","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00189"},{"key":"ref47","first-page":"4247","article-title":"Learning latent subevents in activity videos using temporal attention filters","author":"piergiovanni","year":"0","journal-title":"Proc Assoc Advance Artif Intell"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.155"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20893-6_23"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9238041\/08955791.pdf?arnumber=8955791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:55:19Z","timestamp":1651074919000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8955791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11]]},"references-count":76,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.2965434","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11]]}}}