{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:03:03Z","timestamp":1760709783382,"version":"3.37.3"},"reference-count":115,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012234","name":"Shenzhen Peacock Plan","doi-asserted-by":"publisher","award":["20130408-183003656"],"award-info":[{"award-number":["20130408-183003656"]}],"id":[{"id":"10.13039\/501100012234","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Laboratory for Intelligent Multimedia and Virtual Reality","award":["ZDSYS-201703031405467"],"award-info":[{"award-number":["ZDSYS-201703031405467"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U-1613209"],"award-info":[{"award-number":["U-1613209"]}],"id":[{"id":"10.13039\/501100001809","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":[[2020,1]]},"DOI":"10.1109\/tcsvt.2018.2887061","type":"journal-article","created":{"date-parts":[[2018,12,18]],"date-time":"2018-12-18T00:56:31Z","timestamp":1545094591000},"page":"117-130","source":"Crossref","is-referenced-by-count":11,"title":["Fast and Accurate Action Detection in Videos With Motion-Centric Attention Model"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9464-4426","authenticated-orcid":false,"given":"Jinzhuo","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2664-4413","authenticated-orcid":false,"given":"Wenmin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wen","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.11.014"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2502839"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2665359"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2011.2129370"},{"key":"ref31","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"2015","journal-title":"Proc NIPS"},{"key":"ref30","first-page":"1462","article-title":"DRAW: A recurrent neural network for image generation","author":"gregor","year":"2015","journal-title":"Proc ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2409012"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2424054"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2589838"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2539758"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.133.4.694"},{"journal-title":"Neurobiology of Attention","year":"2005","author":"itti","key":"ref27"},{"key":"ref29","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc NIPS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/BigMM.2017.17"},{"key":"ref22","first-page":"1576","article-title":"Beyond Monte Carlo tree search: Playing go with deep alternative neural network and long-term evaluation","author":"wang","year":"2017","journal-title":"Proc AAAI"},{"key":"ref21","first-page":"418","article-title":"Aligned local descriptors and hierarchical global features for person re-identification","author":"zhang","year":"2017","journal-title":"Advances in Multimedia Information Processing"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/0042-6989(82)90079-7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.177"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/science.7053571"},{"article-title":"The LEAR submission at THUMOS 2014","year":"2014","author":"oneata","key":"ref100"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-5379-7_8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.30"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2854918"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1023-9"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.442"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_37"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.10.002"},{"key":"ref4","first-page":"6","article-title":"Fast saliency based pooling of fisher encoded dense trajectories","volume":"1","author":"karaman","year":"2014","journal-title":"ECCV THUMOS Workshop"},{"key":"ref3","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"},{"journal-title":"Untrimmed video classification for activity detection submission to activitynet challenge","year":"2016","author":"singh","key":"ref6"},{"key":"ref5","first-page":"1","article-title":"CUHK & SIAT submission for THUMOS 15 action recognition challenge","volume":"3","author":"wang","year":"2015","journal-title":"THUMOS Action Recognition challenge"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.10.004"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2247390"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.342"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2295753"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539881"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5244\/C.23.124"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206779"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459335"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2015.00028"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2333151"},{"journal-title":"Survey on the attention based rnn model and its applications in computer vision","year":"2016","author":"wang","key":"ref72"},{"journal-title":"Translating videos to natural language using deep recurrent neural networks","year":"2014","author":"venugopalan","key":"ref71"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126737"},{"journal-title":"Hierarchical attention network for action recognition in videos","year":"2016","author":"wang","key":"ref76"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019335"},{"journal-title":"Action recognition using visual attention","year":"2015","author":"sharma","key":"ref74"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-64698-5_8"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/453"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref62","first-page":"811","article-title":"Deep alternative neural network: Exploring contexts as early as possible for action recognition","author":"wang","year":"2016","journal-title":"Proc NIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532921"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305029"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2855081"},{"key":"ref66","first-page":"1","article-title":"University of Amsterdam at THUMOS challenge 2014","author":"jain","year":"2014","journal-title":"ECCV THUMOS Challenge"},{"key":"ref67","article-title":"Thumos challenge: Action recognition with a large number of classes","author":"gorban","year":"2015","journal-title":"Proc CVPR Workshop"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref2","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"2014","journal-title":"Proc NIPS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123349"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"journal-title":"Temporal activity detection in untrimmed videos with recurrent neural networks","year":"2016","author":"montes","key":"ref109"},{"journal-title":"Hidden two-stream convolutional networks for action recognition","year":"2017","author":"zhu","key":"ref95"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.617"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.337"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.119"},{"journal-title":"Ucf101 A Dataset of 101 Human Actions Classes from Videos in the Wild","year":"2012","author":"soomro","key":"ref92"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.211"},{"article-title":"Thumos challenge: Action recognition with a large number of classes","year":"2014","author":"jiang","key":"ref91"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806226"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.29"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.341"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.338"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.317"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2006.479"},{"key":"ref96","first-page":"10","article-title":"Torch7: A matlab-like environment for machine learning","author":"collobert","year":"2011","journal-title":"NIPS Workshop BigLearn"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref12","first-page":"1","article-title":"Learning class-specific pooling shapes for image classification","author":"wang","year":"2015","journal-title":"Proc ICME"},{"key":"ref13","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7350932"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351407"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2882061"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3132384.3132385"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2544099"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.103"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305028"},{"key":"ref83","first-page":"2593","article-title":"Learning wake-sleep recurrent attention models","author":"ba","year":"2015","journal-title":"Proc NIPS"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1145\/2671188.2749404"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298735"},{"journal-title":"Pose-conditioned spatio-temporal attention for human action recognition","year":"2017","author":"baradel","key":"ref80"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_47"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1126\/science.1242072"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.332"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727234"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/8951039\/08579103.pdf?arnumber=8579103","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:14Z","timestamp":1651070354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8579103\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1]]},"references-count":115,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2018.2887061","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2020,1]]}}}