{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T09:29:32Z","timestamp":1768987772965,"version":"3.49.0"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2017,12,1]],"date-time":"2017-12-01T00:00:00Z","timestamp":1512086400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100011039","name":"Intelligence Advanced Research Projects Activity (IARPA)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011039","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000005","name":"Department of Defense","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"U.S. Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-12-C-0012"],"award-info":[{"award-number":["W911NF-12-C-0012"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011039","name":"IARPA","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100011039","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000005","name":"DoD","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005423","name":"ARL","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005423","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000183","name":"ARO","doi-asserted-by":"publisher","award":["#W911NF-12-1-0241"],"award-info":[{"award-number":["#W911NF-12-1-0241"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","award":["#N000141210066"],"award-info":[{"award-number":["#N000141210066"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"publisher","award":["IIS-1065243"],"award-info":[{"award-number":["IIS-1065243"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"publisher","award":["1451412"],"award-info":[{"award-number":["1451412"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"publisher","award":["1513966"],"award-info":[{"award-number":["1513966"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1139148"],"award-info":[{"award-number":["CCF-1139148"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alfred P. Sloan Research"},{"DOI":"10.13039\/501100012166","name":"973 Program","doi-asserted-by":"crossref","award":["2013CB329503"],"award-info":[{"award-number":["2013CB329503"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61621136008"],"award-info":[{"award-number":["61621136008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61473167"],"award-info":[{"award-number":["61473167"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"German Research Foundation (DFG)","doi-asserted-by":"publisher","award":["DFC TRR-169"],"award-info":[{"award-number":["DFC TRR-169"]}],"id":[{"id":"10.13039\/501100001659","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":[[2017,12,1]]},"DOI":"10.1109\/tpami.2016.2642953","type":"journal-article","created":{"date-parts":[[2016,12,21]],"date-time":"2016-12-21T21:52:49Z","timestamp":1482357169000},"page":"2321-2334","source":"Crossref","is-referenced-by-count":124,"title":["Aligning Where to See and What to Tell: Image Captioning with Region-Based Attention and Scene-Specific Contexts"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2305-1017","authenticated-orcid":false,"given":"Kun","family":"Fu","sequence":"first","affiliation":[]},{"given":"Junqi","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Runpeng","family":"Cui","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Sha","sequence":"additional","affiliation":[]},{"given":"Changshui","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref38","first-page":"26","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc ACL Workshop Text Summarization Branches Out"},{"key":"ref33","first-page":"993","article-title":"Latent Dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.414"},{"key":"ref37","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":"ref36","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-5010"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553505"},{"key":"ref10","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015"},{"key":"ref40","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref11","first-page":"1106","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref12","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref13","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref15","first-page":"1017","article-title":"Generating text with recurrent neural networks","author":"sutskever","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref16","first-page":"139","article-title":"Collecting image annotations using Amazon's Mechanical Turk","author":"rashtchian","year":"2010","journal-title":"NAACL HLT Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1162\/tacl_a_00166","article-title":"From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions","volume":"2","author":"young","year":"2014","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref18","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc 13th Eur Conf Comput Vis"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref28","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref27","first-page":"2204","article-title":"Recurrent models of visual attention","author":"mnih","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref6","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.277"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref20","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","author":"li","year":"2011","journal-title":"Proc 15th Conf Computational Natural Language Learning"},{"key":"ref22","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"2012","journal-title":"Proc 13th Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref21","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"2011","journal-title":"Proc Conf Empirical Methods Natural Language Process"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2017"},{"key":"ref24","first-page":"359","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"2012","journal-title":"Proc 50th Annu Meeting Assoc for Comput Linguist Long Papers-Vol 1"},{"key":"ref41","article-title":"Theano: A Python framework for fast computation of mathematical expressions","year":"0","journal-title":"T development team"},{"key":"ref23","first-page":"1292","article-title":"Image description using visual dependency representations","author":"elliott","year":"2013","journal-title":"Proc Conf Empirical Methods Natural Language Process"},{"key":"ref26","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2015"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1162\/tacl_a_00188","article-title":"TREETALK: Composition and compression of trees for image descriptions","volume":"2","author":"kuznetsova","year":"2014","journal-title":"Transactions of the Association for Computational Linguistics"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/ieeexplore.ieee.org\/ielaam\/34\/8094206\/7792748-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8094206\/07792748.pdf?arnumber=7792748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:47:36Z","timestamp":1649443656000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7792748\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,1]]},"references-count":42,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2642953","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12,1]]}}}