{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:26:27Z","timestamp":1762323987554,"version":"3.37.3"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2018,2,1]],"date-time":"2018-02-01T00:00:00Z","timestamp":1517443200000},"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":["61303154"],"award-info":[{"award-number":["61303154"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2018,2]]},"DOI":"10.1109\/tcsvt.2016.2613125","type":"journal-article","created":{"date-parts":[[2016,9,23]],"date-time":"2016-09-23T14:58:47Z","timestamp":1474642727000},"page":"428-438","source":"Crossref","is-referenced-by-count":33,"title":["Image Class Prediction by Joint Object, Context, and Background Modeling"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1161-8995","authenticated-orcid":false,"given":"Chunjie","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Guibo","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Chao","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"3871","article-title":"Spatially regularized streaming sensor selection","author":"li","year":"2016","journal-title":"Proc AAAI"},{"key":"ref38","doi-asserted-by":"crossref","first-page":"2338","DOI":"10.1109\/TPAMI.2014.2327975","article-title":"Bin ratio-based histogram distances and their application to image classification","volume":"36","author":"hu","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.42"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref31","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc ICLR"},{"key":"ref30","first-page":"392","article-title":"Multi-scale orderless pooling of deep convolutional activation features","author":"gong","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539967"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408875"},{"article-title":"Caltech-256 object category dataset","year":"2007","author":"griffin","key":"ref34"},{"key":"ref28","first-page":"391","article-title":"Edge boxes: Locating object proposals from edges","author":"zitnick","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref27","first-page":"3286","article-title":"BING: Binarized normed gradients for objectness estimation at 300 fps","author":"cheng","year":"2014","journal-title":"Proc Comput Vis Pattern Recognit"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238663"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.110"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2572000"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.16"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2090535"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.175"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2511585"},{"key":"ref25","article-title":"Elastic net hypergraph learning for image clustering and semi-supervised classification","author":"liu","year":"2016","journal-title":"CoRR arXiv 1603 01096"},{"key":"ref50","first-page":"494","article-title":"Mid-level visual element discovery as discriminative mode seeking","author":"doersch","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.476"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2433538"},{"key":"ref58","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.301"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995484"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_17"},{"key":"ref54","doi-asserted-by":"crossref","first-page":"1489","DOI":"10.1109\/TPAMI.2010.224","article-title":"Centrist: A visual descriptor for scene categorization","volume":"33","author":"wu","year":"2011","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref53","first-page":"487","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2014.131"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2012.09.007"},{"key":"ref11","first-page":"1","article-title":"Return of the devil in the details: Delving deep into convolutional nets","author":"chatfield","year":"2014","journal-title":"Proc BMVC"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2376517"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.154"},{"key":"ref13","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.02.013"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366122"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2218822"},{"key":"ref17","first-page":"1","article-title":"Object-centric spatial pooling for image classification","author":"russakovsky","year":"2012","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_57"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2343217"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.132"},{"article-title":"The PASCAL visual object classes challenge 2007 (VOC 2007) results","year":"2007","author":"everingham","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref5","first-page":"1794","article-title":"Linear spatial pyramid matching using sparse coding for image classification","author":"yang","year":"2009","journal-title":"Proc Comput Vis Pattern Recognit"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.63"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2485783"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.140"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2545112"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248111"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.141"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882267"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206537"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref41","first-page":"2570","article-title":"Learning ordinal discriminative features for age estimation","author":"li","year":"2012","journal-title":"Proc Comput Vis Pattern Recognit"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587598"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/8290598\/07575687.pdf?arnumber=7575687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:41:47Z","timestamp":1641987707000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7575687\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2]]},"references-count":59,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2016.2613125","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"type":"print","value":"1051-8215"},{"type":"electronic","value":"1558-2205"}],"subject":[],"published":{"date-parts":[[2018,2]]}}}