{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:35Z","timestamp":1740132875623,"version":"3.37.3"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":["#61773377","#61573352","#91646207","#91438105"],"award-info":[{"award-number":["#61773377","#61573352","#91646207","#91438105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1109\/tmm.2019.2907060","type":"journal-article","created":{"date-parts":[[2019,3,25]],"date-time":"2019-03-25T22:28:14Z","timestamp":1553552894000},"page":"2504-2517","source":"Crossref","is-referenced-by-count":25,"title":["Weakly Semantic Guided Action Recognition"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7558-4448","authenticated-orcid":false,"given":"Tingzhao","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Da","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huxiang","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiming","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhong","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.03.013"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref71","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"srivastava","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref76","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"arXiv 1705 06950"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref39","article-title":"Convnet architecture search for spatiotemporal feature learning","author":"tran","year":"2017","journal-title":"arXiv 1605 08140"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref38","first-page":"4263","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"song","year":"0","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref33","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video classification","author":"yue","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"key":"ref32","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"feichtenhofer","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref30","article-title":"Towards good practices for very deep two-stream convnets","author":"wang","year":"2015","journal-title":"ArXiv 1507 02159"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25446-8_4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","first-page":"1187","article-title":"Learning end-to-end video classification with rank-pooling","author":"fernando","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref62","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.280"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.61"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(92)90344-8"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.339"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"ref66","first-page":"293","article-title":"Joint action recognition and pose estimation from video","author":"bruce","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis Pattern Recognit"},{"key":"ref29","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","first-page":"3324","article-title":"Action recognition with joints-pooled 3D deep convolutional descriptors","author":"cao","year":"0","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.522"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2756840"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749159"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2751969"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2389413"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.852470"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1109\/TCSVT.2014.2381471","article-title":"Background prior-based salient object detection via deep reconstruction residual","volume":"25","author":"han","year":"2015","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref50","article-title":"Action recognition using visual attention","author":"sharma","year":"2015","journal-title":"arXiv 1511 04119"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref59","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":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2333151"},{"key":"ref54","article-title":"Temporal attention filters for human activity recognition in videos","author":"piergiovanni","year":"2016","journal-title":"arXiv 1605 08140"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.604"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.94"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238378"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2666739"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref13","first-page":"28","article-title":"Action detection in complex scenes with spatial and temporal ambiguities","author":"hu","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1291233.1291311"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.253"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2626959"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2527340"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2669658"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2389765"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2670782"},{"key":"ref49","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8296542"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref45","first-page":"296","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question","author":"gao","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","first-page":"577","article-title":"Attention-based models for speech recognition","author":"chorowski","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126299"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.108"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2636150"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8846791\/08673575.pdf?arnumber=8673575","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T20:47:06Z","timestamp":1657745226000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8673575\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10]]},"references-count":77,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2019.2907060","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2019,10]]}}}