{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:32:56Z","timestamp":1792787576317,"version":"4.5.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2017,4,1]],"date-time":"2017-04-01T00:00:00Z","timestamp":1491004800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/100007065","name":"NVIDIA","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007065","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GPUs"},{"DOI":"10.13039\/100000006","name":"ONR","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014036","name":"MURI","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100014036","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000001","name":"US National Science Foundation","doi-asserted-by":"publisher","award":["ISS-1115313"],"award-info":[{"award-number":["ISS-1115313"]}],"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":[[2017,4,1]]},"DOI":"10.1109\/tpami.2016.2598339","type":"journal-article","created":{"date-parts":[[2016,8,5]],"date-time":"2016-08-05T18:25:02Z","timestamp":1470421502000},"page":"664-676","source":"Crossref","is-referenced-by-count":604,"title":["Deep Visual-Semantic Alignments for Generating Image Descriptions"],"prefix":"10.1109","volume":"39","author":[{"given":"Andrej","family":"Karpathy","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Fei-Fei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.211"},{"key":"ref38","first-page":"1671","article-title":"A joint model of language and perception for grounded attribute learning","author":"matuszek","year":"0","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref33","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref30","article-title":"Learning a recurrent visual representation for image caption generation","author":"chen","year":"2014","journal-title":"CoRR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.340"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.455"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315253"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref61","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref28","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref27","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","author":"mitchell","year":"0","journal-title":"Proc 13th Conf Eur Chapter Assoc Comput Linguistics"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref66","article-title":"Microsoft Coco captions: Data collection and evaluation server","author":"chen","year":"2015","journal-title":"arXiv 1504 00325"},{"key":"ref29","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref67","article-title":"Exploring nearest neighbor approaches for image captioning","author":"devlin","year":"2015"},{"key":"ref68","first-page":"1681","article-title":"Torch7: A Matlab-like environment for machine learning","author":"collobert","year":"0","journal-title":"Proc Big Learn Advances Neural Inf Process Syst Workshop"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1167\/7.1.10"},{"key":"ref20","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","author":"li","year":"0","journal-title":"Proc 15th Conf Computational Natural Language Learning"},{"key":"ref22","first-page":"1292","article-title":"Image description using visual dependency representations","author":"elliott","year":"0","journal-title":"Proc Empirical Methods Natural Language Process"},{"key":"ref21","article-title":"Video in sentences out","author":"barbu","year":"2012"},{"key":"ref24","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"0","journal-title":"Proc Conf Empirical Methods Natural Language Process"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34500-5_24"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/S14-1015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2050411"},{"key":"ref50","first-page":"1017","article-title":"Generating text with recurrent neural networks","author":"sutskever","year":"0","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref59","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","author":"krishna","year":"2016"},{"key":"ref58","article-title":"Lecture 6.5-RmsProp: Divide the gradient by a running average of its recent magnitude","author":"tieleman","year":"2012"},{"key":"ref57","article-title":"Lecture 6.5rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Networks for Machine Learning"},{"key":"ref56","author":"zhang","year":"1999","journal-title":"State-space Search Algorithms Complexity Extensions and Applications"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref52","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"0","journal-title":"Proc IEEE Conf Comput Vis Pattern Recog"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.260"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459211"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408872"},{"key":"ref14","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":"ref15","first-page":"2407","article-title":"Learning cross-modality similarity for multinomial data","author":"jia","year":"0","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref16","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1162\/tacl_a_00177","article-title":"Grounded compositional semantics for finding and describing images with sentences","volume":"2","author":"socher","year":"2014","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref18","first-page":"359","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"0","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref19","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"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref6","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 Artificial Intell Res"},{"key":"ref5","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":"ref8","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":"ref7","article-title":"Learning a recurrent visual representation for image caption generation","author":"chen","year":"2014"},{"key":"ref49","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"0","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref9","first-page":"1107","article-title":"Matching words and pictures","volume":"3","author":"barnard","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref46","first-page":"1532","article-title":"Glove: Global vectors for word representation","author":"socher","year":"0","journal-title":"Proc Empirical Methods Natural Language Process"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-33486-6_6"},{"key":"ref48","first-page":"1137","article-title":"A neural probabilistic language model","volume":"3","author":"bengio","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref47","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","author":"mikolov","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref42","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref41","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7870775\/07534740.pdf?arnumber=7534740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:08:20Z","timestamp":1642003700000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7534740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,1]]},"references-count":68,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2598339","relation":{},"ISSN":["0162-8828","2160-9292"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,4,1]]}}}