{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T10:44:35Z","timestamp":1788777875639,"version":"build-2803163510"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2017,9,1]],"date-time":"2017-09-01T00:00:00Z","timestamp":1504224000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-08-C-0135-S8"],"award-info":[{"award-number":["HR0011-08-C-0135-S8"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-10-C-0112"],"award-info":[{"award-number":["HR0011-10-C-0112"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-13-1-0395"],"award-info":[{"award-number":["W911NF-13-1-0395"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2017,9,1]]},"DOI":"10.1109\/tpami.2016.2616308","type":"journal-article","created":{"date-parts":[[2016,10,11]],"date-time":"2016-10-11T15:25:54Z","timestamp":1476199554000},"page":"1770-1782","source":"Crossref","is-referenced-by-count":38,"title":["Hierarchical Context Modeling for Video Event Recognition"],"prefix":"10.1109","volume":"39","author":[{"given":"Xiaoyang","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"140","article-title":"Convolutional learning of spatio-temporal features","author":"taylor","year":"2010","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00311"},{"key":"ref32","first-page":"448","article-title":"Deep Boltzmann machines","author":"salakhutdinov","year":"2009","journal-title":"Proc 12th Int Conf Artif Intell Statist"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0596-6"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref34","first-page":"153","article-title":"Greedy layer-wise training of deep networks","author":"bengio","year":"2007","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_51"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383132"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-004-0148-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0510-7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995586"},{"key":"ref20","article-title":"UT-interaction dataset, ICPR contest on semantic description of human activities","author":"ryoo","year":"2010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.137"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.228"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.05.001"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.72"},{"key":"ref26","first-page":"2004","article-title":"Hierarchical spatio-temporal context modeling for action recognition","author":"sun","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.320"},{"key":"ref50","author":"salakhutdinov","year":"0"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587756"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.445"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.342"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_50"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1007\/978-3-642-17711-8_31","article-title":"Variations of a Hough-voting action recognition system","author":"waltisberg","year":"2010","journal-title":"Recognizing Patterns in Signals, Speech, Images and Videos"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459361"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247816"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2012.40"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995493"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.322"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383331"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1023052124951"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587609"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.873"},{"key":"ref17","first-page":"3378","article-title":"Incorporating contextual knowledge to dynamic Bayesian networks for event recognition","author":"wang","year":"2012","journal-title":"Proc 21st Int Conf Pattern Recognit"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.07.015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/34.993558"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.1998.670984"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref6","first-page":"1331","article-title":"Conditional random fields for activity recognition","author":"vail","year":"2007","journal-title":"Proc Int Joint Conf Autonomous Agents and Multiagent Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2010.01.011"},{"key":"ref7","first-page":"359","article-title":"Recognition and segmentation of 3D human action using hmm and multi-class adaboost","author":"lv","year":"2006","journal-title":"Proc 9th Eur Conf Comput Vis"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539881"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.22"},{"key":"ref45","first-page":"695","article-title":"Multiscale conditional random fields for image labeling","author":"he","year":"2004","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299071"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.328"},{"key":"ref42","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_46"},{"key":"ref44","first-page":"2949","article-title":"Multimodal learning with deep Boltzmann machines","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref43","first-page":"2222","article-title":"Multimodal learning with deep Boltzmann machines","author":"srivastava","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8000766\/07588132.pdf?arnumber=7588132","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:40:56Z","timestamp":1641987656000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7588132\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,1]]},"references-count":62,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2616308","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,1]]}}}