{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T18:10:32Z","timestamp":1792865432721,"version":"4.5.0"},"reference-count":49,"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\/OAPA.html"}],"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.2016.2587640","type":"journal-article","created":{"date-parts":[[2016,7,7]],"date-time":"2016-07-07T20:16:32Z","timestamp":1467922592000},"page":"652-663","source":"Crossref","is-referenced-by-count":639,"title":["Show and Tell: Lessons Learned from the 2015 MSCOCO Image Captioning Challenge"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7848-7283","authenticated-orcid":false,"given":"Oriol","family":"Vinyals","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Toshev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samy","family":"Bengio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dumitru","family":"Erhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref33","first-page":"1735","article-title":"Mind's eye: A recurrent visual representation for image caption generation","volume":"9","author":"chen","year":"1997","journal-title":"Neural Comput"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref31","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref37","article-title":"Generating sequences with recurrent neural networks","author":"graves","year":"2013"},{"key":"ref36","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"International Conference on Learning Representations"},{"key":"ref35","article-title":"Decaf: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2017"},{"key":"ref28","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2015","journal-title":"International Conference on Learning Representations"},{"key":"ref27","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014"},{"key":"ref29","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2015","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref2","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 Part IV"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref20","article-title":"Technical report: Image captioning with semantically similar images","author":"kol\u00e1?","year":"2015"},{"key":"ref22","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","author":"karpathy","year":"2014","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref21","article-title":"Grounded compositional semantics for finding and describing images with sentences","author":"socher","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref24","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref26","article-title":"Multimodal neural language models","author":"kiros","year":"0","journal-title":"Proc Neural Inf Process Syst Deep Learn Workshop"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref10","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","author":"li","year":"0","journal-title":"Proc Computational Natural Language Learning"},{"key":"ref11","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":"ref40","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","volume":"29","author":"banerjee","year":"0","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref12","first-page":"1250","article-title":"Generating image descriptions using dependency relational patterns","author":"aker","year":"0","journal-title":"Proc 48th Ann Meeting of the Assoc Computational Linguistics"},{"key":"ref13","first-page":"359","article-title":"Collective generation of natural image descriptions","author":"kuznetsova","year":"0","journal-title":"Proc 50th Annu Meeting Assoc for Comput Linguist Long Papers-Vol 1"},{"key":"ref14","article-title":"Treetalk: Composition and compression of trees for image descriptions","volume":"2","author":"kuznetsova","year":"0","journal-title":"Proc Assoc Comput Linguistics"},{"key":"ref15","first-page":"1292","article-title":"Image description using visual dependency representations","author":"elliott","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref16","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":"ref17","first-page":"529","article-title":"Improving image-sentence embeddings using large weakly annotated photo collections","author":"gong","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref18","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref19","article-title":"Exploring nearest neighbor approaches for image captioning","author":"devlin","year":"2015"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref6","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1996.561027"},{"key":"ref7","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2013"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/BF00058655"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2050411"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref45","article-title":"Recurrent neural network regularization","author":"zaremba","year":"2014"},{"key":"ref48","article-title":"Going deeper with convolutions","author":"szegedy","year":"2014"},{"key":"ref47","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref42","first-page":"139","article-title":"Collecting image annotations using Amazon's Mechanical Turk","author":"rashtchian","year":"0","journal-title":"NAACL HLT Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk"},{"key":"ref41","article-title":"Rouge: A package for automatic evaluation of summaries","volume":"8","author":"lin","year":"0","journal-title":"Proc ACL Workshop Text Summarization Branches Out"},{"key":"ref44","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-10602-1_48","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014"},{"key":"ref43","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"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/7870775\/07505636.pdf?arnumber=7505636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:26:19Z","timestamp":1642004779000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7505636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,1]]},"references-count":49,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2016.2587640","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]]}}}