{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T12:36:29Z","timestamp":1783427789970,"version":"3.54.6"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2017,2,1]],"date-time":"2017-02-01T00:00:00Z","timestamp":1485907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,2,1]],"date-time":"2017-02-01T00:00:00Z","timestamp":1485907200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,2,1]],"date-time":"2017-02-01T00:00:00Z","timestamp":1485907200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2017,2,1]],"date-time":"2017-02-01T00:00:00Z","timestamp":1485907200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1212948"],"award-info":[{"award-number":["IIS-1212948"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-091686"],"award-info":[{"award-number":["IIS-091686"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2017,2]]},"DOI":"10.1109\/tip.2016.2628585","type":"journal-article","created":{"date-parts":[[2016,11,14]],"date-time":"2016-11-14T19:11:22Z","timestamp":1479150682000},"page":"619-632","source":"Crossref","is-referenced-by-count":24,"title":["A Context-Driven Extractive Framework for Generating Realistic Image Descriptions"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5932-2491","authenticated-orcid":false,"given":"Amara","family":"Tariq","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hassan","family":"Foroosh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540000"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47979-1_7"},{"key":"ref33","volume":"293","author":"mani","year":"1999","journal-title":"Advances in Automatic Text Summarization"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025616"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32498-7_36"},{"key":"ref30","first-page":"172","article-title":"Apples to oranges: Evaluating image annotations from natural language processing systems","author":"mason","year":"2012","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technol"},{"key":"ref37","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":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1006\/cogp.1997.0667"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2008.916999"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2101051"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2443501"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2188038"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2206040"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2255302"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2183880"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2180916"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2262289"},{"key":"ref18","first-page":"553","article-title":"A model for learning the semantics of pictures","author":"lavrenko","year":"2003","journal-title":"Proc 17th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref19","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.118"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33712-3_60"},{"key":"ref27","first-page":"831","article-title":"Topic models for image annotation and text illustration","author":"feng","year":"2010","journal-title":"Proc Human Lang Technol Annu Conf North Amer Chapter Assoc Comput Linguistics"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459266"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2103082"},{"key":"ref29","first-page":"647","article-title":"Text mining for automatic image tagging","author":"leong","year":"2010","journal-title":"Proc 23rd Int Conf Comput Linguistics Posters"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2375641"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2428055"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2045169"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315274"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2011.2170557"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995312"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_7"},{"key":"ref20","first-page":"1","article-title":"A multimodal LDA model integrating textual, cognitive and visual modalities","volume":"18","author":"roller","year":"2003","journal-title":"J Artif Intell Res"},{"key":"ref45","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":"ref48","volume":"1","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1613\/jair.3994","article-title":"Framing image description as a ranking task: Data, models and evaluation metrics","volume":"47","author":"hodosh","year":"2013","journal-title":"J Artif Intell Res"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref42","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref41","first-page":"790","article-title":"Generalizing image captions for image-text parallel corpus","author":"kuznetsova","year":"2013","journal-title":"Proc ACL"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2393347.2393424"},{"key":"ref44","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Proc CVPR"},{"key":"ref26","first-page":"272","article-title":"Automatic image annotation using auxiliary text information","author":"feng","year":"2008","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref43","year":"2005","journal-title":"Global Autonomous Language Exploitation (GALE) DARPA\/IPTO Proposer Information Pamphlet"},{"key":"ref25","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"karpathy","year":"2014"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/83\/7763897\/7742967-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/7763897\/07742967.pdf?arnumber=7742967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:48:24Z","timestamp":1649443704000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7742967\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2]]},"references-count":48,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tip.2016.2628585","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2]]}}}