{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:05:07Z","timestamp":1766066707838,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2017,5,1]],"date-time":"2017-05-01T00:00:00Z","timestamp":1493596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["FT130101530"],"award-info":[{"award-number":["FT130101530"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61572108","61632007"],"award-info":[{"award-number":["61572108","61632007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Thousand-Young-Talents Program of China"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["ZYGX2014Z007","ZYGX2015J055"],"award-info":[{"award-number":["ZYGX2014Z007","ZYGX2015J055"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2017,5]]},"DOI":"10.1109\/tip.2017.2670782","type":"journal-article","created":{"date-parts":[[2017,2,17]],"date-time":"2017-02-17T19:52:44Z","timestamp":1487361164000},"page":"2149-2162","source":"Crossref","is-referenced-by-count":29,"title":["Hierarchical Latent Concept Discovery for Video Event Detection"],"prefix":"10.1109","volume":"26","author":[{"given":"Chao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiewei","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoshuai","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9872-8451","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref38","first-page":"392","article-title":"Modeling temporal structure of decomposable motion segments for activity classification","author":"niebles","year":"2010","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383266"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.330"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247808"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2295753"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.207"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540039"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref27","first-page":"1746","article-title":"Learning to detect concepts from Webly-labeled video data","author":"liang","year":"2016","journal-title":"Proc Int Joint Conf Artif Intell"},{"key":"ref29","first-page":"428","article-title":"Human detection using oriented histograms of flow and appearance","author":"dalal","year":"2006","journal-title":"Proc 9th Eur Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-012-0024-2"},{"year":"2016","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247814"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248114"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.288"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.339"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-014-2010-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_44"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553523"},{"key":"ref51","first-page":"3539","article-title":"Regularized bundle methods for convex and non-convex risks","volume":"13","author":"do","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995496"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1991996.1992025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref53","first-page":"1627","article-title":"Structured prediction, dual extragradient and Bregman projections","volume":"7","author":"taskar","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553408"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2449660"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2511585"},{"key":"ref40","first-page":"843","article-title":"Unsupervised learning of video representations using lstms","author":"srivastava","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2323014"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.287"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.453"},{"key":"ref15","first-page":"430","article-title":"Recognizing complex events using large margin joint low-level event model","author":"izadinia","year":"2012","journal-title":"Proc 12th Eur Conf Comput Vis"},{"key":"ref16","article-title":"Exploiting feature and class relationships in video categorization with regularized deep neural networks","author":"jiang","year":"2015","journal-title":"CoRR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964319"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.334"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2614136"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-005-1838-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref7","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Annu Conf Adv Neural Inf Process Syst"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015341"},{"key":"ref9","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc 31st IEEE Int Conf Mach Learn"},{"key":"ref46","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"CoRR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298789"},{"key":"ref47","first-page":"1269","article-title":"Aggregating local deep features for image retrieval","author":"babenko","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.508"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806221"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.272"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995499"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/7893836\/07858791.pdf?arnumber=7858791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:14:13Z","timestamp":1642004053000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7858791\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,5]]},"references-count":57,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tip.2017.2670782","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2017,5]]}}}