{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:01:49Z","timestamp":1783180909482,"version":"3.54.6"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,6]]},"DOI":"10.1109\/cvpr.2011.5995466","type":"proceedings-article","created":{"date-parts":[[2011,8,25]],"date-time":"2011-08-25T16:42:30Z","timestamp":1314290550000},"page":"1601-1608","source":"Crossref","is-referenced-by-count":341,"title":["Baby talk: Understanding and generating simple image descriptions"],"prefix":"10.1109","author":[{"given":"Girish","family":"Kulkarni","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Visruth","family":"Premraj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sagnik","family":"Dhar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yejin","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander C","family":"Berg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tamara L","family":"Berg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206594"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.200"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459250"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587799"},{"key":"16","article-title":"Beyond nouns: Exploiting prepositions and comparative adjectives for learning visual classifiers","author":"gupta","year":"2008","journal-title":"ECCV"},{"key":"13","first-page":"1239","article-title":"How many words is a picture worth? Automatic caption generation for news images","author":"feng","year":"2010","journal-title":"Pr ACL ACL'10"},{"key":"14","article-title":"Learning visual attributes","author":"ferrari","year":"2007","journal-title":"NIPS"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1167\/4.8.863"},{"key":"12","author":"felzenszwalb","year":"0","journal-title":"Discriminatively Trained Deformable Part Models Release 4"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0109-1"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.3115\/1705475.1705482"},{"key":"23","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2008.128","article-title":"80 million tiny images: A large dataset for non-parametric object and scene recognition","volume":"30","author":"torralba","year":"2008","journal-title":"TPAMI"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1145\/1666420.1666446"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.856938"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2050411"},{"key":"27","article-title":"Template-filtered headline summarization","author":"zhou","year":"2004","journal-title":"Text Summarization Branches Out Pr ACL-04 Wkshp"},{"key":"3","article-title":"Large language models in machine translation","author":"brants","year":"2007","journal-title":"EMNLP-CoNLL"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1162\/153244303322533214"},{"key":"10","article-title":"Every picture tells a story: Generating sentences for images","author":"farhadi","year":"2010","journal-title":"ECCV"},{"key":"1","first-page":"1250","article-title":"Generating image descriptions using dependency relational patterns","author":"aker","year":"2010","journal-title":"Proc ACL"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459256"},{"key":"6","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"CVPR"},{"key":"5","author":"de marnee","year":"0","journal-title":"Stanford Typed Dependencies manual"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.3115\/1073427.1073430"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206772"},{"key":"8","article-title":"Object recognition as machine translation","author":"duygulu","year":"2002","journal-title":"ECCV"}],"event":{"name":"2011 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Colorado Springs, CO, USA","start":{"date-parts":[[2011,6,20]]},"end":{"date-parts":[[2011,6,25]]}},"container-title":["CVPR 2011"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5968010\/5995307\/05995466.pdf?arnumber=5995466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T01:12:08Z","timestamp":1497921128000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5995466\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,6]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2011.5995466","relation":{},"subject":[],"published":{"date-parts":[[2011,6]]}}}