{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T05:08:22Z","timestamp":1773810502980,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"NSF China","award":["61622204"],"award-info":[{"award-number":["61622204"]}]},{"name":"NSF China","award":["61572134"],"award-info":[{"award-number":["61572134"]}]},{"name":"STCSM, Shanghai","award":["16QA1400500"],"award-info":[{"award-number":["16QA1400500"]}]},{"name":"STCSM, Shanghai","award":["16JC1420401"],"award-info":[{"award-number":["16JC1420401"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/tmm.2018.2823900","type":"journal-article","created":{"date-parts":[[2018,4,12]],"date-time":"2018-04-12T20:25:38Z","timestamp":1523564738000},"page":"3137-3147","source":"Crossref","is-referenced-by-count":109,"title":["Modeling Multimodal Clues in a Hybrid Deep Learning Framework for Video Classification"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-8567","authenticated-orcid":false,"given":"Yu-Gang","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Zuxuan","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xiangyang","family":"Xue","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1444-1205","authenticated-orcid":false,"given":"Shih-Fu","family":"Chang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0723-7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.109"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.228"},{"key":"ref36","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref35","first-page":"4694","article-title":"Beyond short snippets: Deep networks for video\n classification","author":"ng","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref34","first-page":"178.1","article-title":"Event\n fisher vectors: Robust encoding visual diversity of visual streams","author":"nagel","year":"0","journal-title":"Proc BMVC"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.427"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2234731"},{"key":"ref63","first-page":"3021","article-title":"Robust late fusion with rank minimization","author":"ye","year":"0","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.288"},{"key":"ref64","first-page":"60.1","article-title":"Exploiting image-trained CNN\n architectures for unconstrained video classification","author":"zha","year":"0","journal-title":"Proc BMVC"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-006-9794-4"},{"key":"ref29","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 Vis and Pattern Recog"},{"key":"ref2","first-page":"54.1","article-title":"Return of the devil in the details:\n Delving deep into convolutional nets","author":"chatfield","year":"0","journal-title":"Proc BMVC"},{"key":"ref1","first-page":"437","article-title":"Practical recommendations for gradient-based training of deep\n architectures","author":"bengio","year":"0","journal-title":"Proc Neural Netw Tricks of the Trade"},{"key":"ref20","article-title":"THUMOS challenge: Action recognition with a\n large number of classes","author":"jiang","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2670560"},{"key":"ref21","first-page":"1420","article-title":"Domain adaptive semantic\n diffusion for large scale context-based video annotation","author":"jiang","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis %"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"ref26","first-page":"953","article-title":"Lp-norm multiple kernel\n learning","volume":"12","author":"kloft","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5244\/C.22.99"},{"key":"ref50","first-page":"4489","article-title":"C3D: Generic features for video analysis","author":"tran","year":"0","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref51","first-page":"235:1","article-title":"Conditional random fields for activity recognition","author":"vail","year":"0","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654931"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206709"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.291"},{"key":"ref55","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 Vis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref52","first-page":"2643","article-title":"Deep\n content-based music recommendation","author":"van den oord","year":"0","journal-title":"Proc 26th Int Conf Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2666540"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.06.042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2671414"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-013-0567-0"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-012-0024-2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2436813"},{"key":"ref4","first-page":"2067","article-title":"Gated feedback recurrent\n neural networks","author":"chung","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.168"},{"key":"ref6","first-page":"428","article-title":"Human\n detection using oriented histograms of flow and appearance","author":"dalal","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref46","first-page":"2222","article-title":"Multimodal learning with deep boltzmann machines","author":"srivastava","year":"0","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref45","first-page":"843","article-title":"Unsupervised learning of video representations using LSTMs","author":"mansimov","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref47","first-page":"3104","article-title":"Sequence to\n Sequence Learning with Neural Networks","author":"sutskever","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref42","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref41","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"simonyan","year":"0","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref44","first-page":"1","article-title":"UCF101: A\n dataset of 101 human actions classes from videos in the wild","volume":"cs cv","author":"soomro","year":"2012","journal-title":"CoRR arXiv org"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101236"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/8491746\/08336920.pdf?arnumber=8336920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T17:34:39Z","timestamp":1643218479000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8336920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":65,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2018.2823900","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11]]}}}