{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:34:08Z","timestamp":1787013248544,"version":"build-2736575974"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2016,3,1]],"date-time":"2016-03-01T00:00:00Z","timestamp":1456790400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSFC","doi-asserted-by":"publisher","award":["61425011"],"award-info":[{"award-number":["61425011"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSFC","doi-asserted-by":"publisher","award":["U1201255"],"award-info":[{"award-number":["U1201255"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSFC","doi-asserted-by":"publisher","award":["61271218"],"award-info":[{"award-number":["61271218"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSFC","doi-asserted-by":"publisher","award":["61529101"],"award-info":[{"award-number":["61529101"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSFC","doi-asserted-by":"publisher","award":["61472234"],"award-info":[{"award-number":["61472234"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSFC","doi-asserted-by":"publisher","award":["61271211"],"award-info":[{"award-number":["61271211"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shu Guanga"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/tmm.2016.2520087","type":"journal-article","created":{"date-parts":[[2016,1,20]],"date-time":"2016-01-20T15:58:16Z","timestamp":1453305496000},"page":"507-520","source":"Crossref","is-referenced-by-count":5,"title":["Joint Inference of Objects and Scenes With Efficient Learning of Text-Object-Scene Relations"],"prefix":"10.1109","volume":"18","author":[{"given":"Botao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongkai","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Y. F.","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.95"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"ref33","first-page":"3","article-title":"Fast exact inference with a factored model for natural language parsing","author":"klein","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.371"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298711"},{"key":"ref37","first-page":"1794","article-title":"Linear spatial pyramid matching using sparse coding for image classification","author":"yang","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.79"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126229"},{"key":"ref34","first-page":"1378","article-title":"Object bank: A high-level image representation for scene classification & semantic feature sparsification","author":"li","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.344"},{"key":"ref40","first-page":"776","article-title":"Efficient object category recognition using classemes","author":"torresani","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref11","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2306655"},{"key":"ref13","first-page":"2036","article-title":"Towards total scene understanding: Classification, annotation and segmentation in an automatic framework","author":"li","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.260"},{"key":"ref15","first-page":"16","article-title":"Beyond nouns: Exploiting prepositions and comparative adjectives for learning visual classifiers","author":"gupta","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref16","first-page":"1957","article-title":"Landmark classification in large-scale image collections","author":"li","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206816"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540120"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101154"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2202676"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.539"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2017128"},{"key":"ref6","first-page":"2397","article-title":"A discriminative latent model of image region and object tag correspondence","author":"wang","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.309"},{"key":"ref5","first-page":"15","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2280895"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2267726"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2310992"},{"key":"ref22","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref21","first-page":"1107","article-title":"Matching words and pictures","volume":"3","author":"barnard","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540000"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/860458.860460"},{"key":"ref26","first-page":"2717","article-title":"A neural autoregressive topic model","author":"larochelle","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref25","first-page":"2407","article-title":"Learning cross-modality similarity for multinomial data","author":"jia","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/7412784\/7387771.pdf?arnumber=7387771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:01:54Z","timestamp":1641985314000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7387771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tmm.2016.2520087","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,3]]}}}