{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T19:23:13Z","timestamp":1770751393840,"version":"3.50.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673062"],"award-info":[{"award-number":["61673062"]}],"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":["61472038"],"award-info":[{"award-number":["61472038"]}],"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":[[2018,6]]},"DOI":"10.1109\/tmm.2017.2771462","type":"journal-article","created":{"date-parts":[[2017,11,8]],"date-time":"2017-11-08T19:18:16Z","timestamp":1510168696000},"page":"1537-1547","source":"Crossref","is-referenced-by-count":45,"title":["Content-Attention Representation by Factorized Action-Scene Network for Action Recognition"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0172-3115","authenticated-orcid":false,"given":"Jingyi","family":"Hou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2056-6947","authenticated-orcid":false,"given":"Xinxiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchao","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunde","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref33","first-page":"20","article-title":"Temporal segment networks: Towards good\n practices for deep action recognition","author":"wang","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref32","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.791201"},{"key":"ref30","first-page":"1933","article-title":"Selection and\n context for action recognition","volume":"9","author":"han","year":"0","journal-title":"Proc IEEE Conf Comput Vision"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref36","article-title":"UCF101: A\n dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"0","journal-title":"arXiv 1212 0402"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_36"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0122-4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.460"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15555-0_11"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.212"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.235"},{"key":"ref23","first-page":"143","article-title":"Improving the fisher kernel for large-scale image classification","author":"perronnin","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref26","article-title":"A comprehensive survey on cross-modal retrieval","author":"wang","year":"0","journal-title":"arXiv 1607 06215"},{"key":"ref25","first-page":"5297","article-title":"Netvlad: CNN architecture for weakly supervised place\n recognition","author":"arandjelovi?","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recogn"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298599"},{"key":"ref51","first-page":"1","article-title":"Action recognition using visual attention","author":"sharma","year":"2016","journal-title":"arXiv 1511 04119"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6238919"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.60"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299176"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref40","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","article-title":"Neural\n turing machines","volume":"abs 1410 5401","author":"graves","year":"2014","journal-title":"CoRR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.04.005"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.238"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.149"},{"key":"ref4","first-page":"2004","article-title":"Hierarchical spatio-temporal context modeling for action\n recognition","author":"sun","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recog"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2326734"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247807"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2482970"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.341"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.336"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2404779"},{"key":"ref46","first-page":"1","article-title":"Theano: New features and speed improvements","author":"bastien","year":"0","journal-title":"Proc NIPS Workshop on Deep Learning and Unsupervised Feature Learning"},{"key":"ref45","first-page":"3471","article-title":"Face video retrieval via deep learning of\n binary hash representations","author":"dong","year":"0","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553510"},{"key":"ref47","first-page":"204","article-title":"Beyond gaussian pyramid: Multi-skip feature stacking for action recognition","author":"lan","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recog"},{"key":"ref42","first-page":"2556","article-title":"Space-time interest points","author":"kuehne","year":"0","journal-title":"Proc IEEE Conf Comput Vision"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2016.03.013"},{"key":"ref44","first-page":"6","article-title":"Deep\n face recognition","volume":"1","author":"parkhi","year":"0","journal-title":"Proc Brit Mach Vision Conf"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70711"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8359225\/08101020.pdf?arnumber=8101020","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:22:40Z","timestamp":1642004560000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8101020\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":55,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2017.2771462","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,6]]}}}