{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:50:44Z","timestamp":1790265044734,"version":"4.1.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T00:00:00Z","timestamp":1459468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T00:00:00Z","timestamp":1459468800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T00:00:00Z","timestamp":1459468800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2016,4,1]],"date-time":"2016-04-01T00:00:00Z","timestamp":1459468800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1341772"],"award-info":[{"award-number":["IIS-1341772"]}],"id":[{"id":"10.13039\/100000001","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":[[2016,4,1]]},"DOI":"10.1109\/tpami.2014.2366143","type":"journal-article","created":{"date-parts":[[2014,10,31]],"date-time":"2014-10-31T19:02:36Z","timestamp":1414782156000},"page":"627-638","source":"Crossref","is-referenced-by-count":43,"title":["Adopting Abstract Images for Semantic Scene Understanding"],"prefix":"10.1109","volume":"38","author":[{"given":"C. Lawrence","family":"Zitnick","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramakrishna","family":"Vedantam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Devi","family":"Parikh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_35"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.232"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459256"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.53.100901.135125"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.190"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.155"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995711"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(82)90007-X"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0090-8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1109\/TPAMI.2010.70","article-title":"Learning to detect a salient object","volume":"33","author":"liu","year":"2011","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref35","volume":"8","author":"einhuser","year":"0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540235"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126508"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.211"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.387"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/nn870"},{"key":"ref28","first-page":"139","article-title":"Collecting image annotations using Amazon's mechanical turk","author":"rashtchian","year":"0","journal-title":"In NAACL HLT Workshop on Creating Speech and Language Data with Amazon's MT"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(02)00052-3"},{"key":"ref27","first-page":"13","article-title":"The IAPR tc-12 benchmark: A new evaluation resource for visual information systems","author":"grubinger","year":"0","journal-title":"Proc Int Workshop OntoImage"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"ref66","article-title":"Contextual models for object detection using boosted random fields","author":"torralba","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref29","article-title":"Microsoft COCO: Common objects in context","volume":"abs 1405 312","author":"lin","year":"2014","journal-title":"CoRR"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1167\/9.7.4"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.09.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/34.877520"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2006.262545"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126281"},{"key":"ref24","first-page":"10","article-title":"Generating natural-language video descriptions using text-mined knowledge","author":"krishnamoorthy","year":"0","journal-title":"Proc Workshop Vis Natural Lang Process"},{"key":"ref23","first-page":"433","author":"rohrbach","year":"0"},{"key":"ref26","year":"0"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88690-7_29"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1360612.1360637"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087172"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540218"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383518"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995467"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1141911.1141933"},{"key":"ref53","author":"renjie","year":"2010"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-6242-2_8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1080\/14640747308400340"},{"key":"ref12","first-page":"663","article-title":"Automatic attribute discovery and characterization from noisy web data","author":"berg","year":"0","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref13","first-page":"16","article-title":"Beyond nouns: Exploiting prepositions and comparative adjectives for learning visual classifiers","author":"gupta","year":"0","journal-title":"Proc 10th Eur Conf Comput Vis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2307\/1416950"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1111\/j.2044-8309.1985.tb00670.x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995721"},{"key":"ref18","first-page":"2429","article-title":"Understanding the intrinsic memorability of images","author":"isola","year":"0","journal-title":"Proc Adv Neural Inform Process Syst"},{"key":"ref19","first-page":"1473","article-title":"Distance metric learning for large margin nearest neighbor classification","author":"weinberger","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0494-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1167\/8.3.3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248100"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-010-0376-0"},{"key":"ref8","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","first-page":"15","article-title":"Every picture tells a story: Generating sentences from images","author":"farhadi","year":"0","journal-title":"Proc 11th Eur Conf Comput Vis"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.102.3.419"},{"key":"ref9","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1006\/jmps.2001.1388"},{"key":"ref45","first-page":"1378","article-title":"Memorability of image regions","author":"khosla","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3758\/BF03209391"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.114.3.539"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0803390105"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2307\/1419366"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.397"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195169669.001.0001"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/34\/7425337\/6942196-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7425337\/06942196.pdf?arnumber=6942196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:47:37Z","timestamp":1649443657000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6942196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,4,1]]},"references-count":76,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2014.2366143","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,4,1]]}}}