{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T18:01:03Z","timestamp":1784656863747,"version":"3.55.0"},"reference-count":142,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000145","name":"Information and Intelligent Systems","doi-asserted-by":"crossref","award":["1651902"],"award-info":[{"award-number":["1651902"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000183","name":"U.S. Army Research Office","doi-asserted-by":"crossref","award":["W911NF-17-1-0367"],"award-info":[{"award-number":["W911NF-17-1-0367"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2019,8]]},"DOI":"10.1109\/tetci.2019.2892755","type":"journal-article","created":{"date-parts":[[2019,1,29]],"date-time":"2019-01-29T03:20:39Z","timestamp":1548732039000},"page":"297-312","source":"Crossref","is-referenced-by-count":81,"title":["Visual to Text: Survey of Image and Video Captioning"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1205-8632","authenticated-orcid":false,"given":"Sheng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5639-7540","authenticated-orcid":false,"given":"Zhiqiang","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5098-2853","authenticated-orcid":false,"given":"Yun","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130425"},{"key":"ref38","first-page":"102","article-title":"Video in sentences out","author":"barbu","year":"0","journal-title":"Proc Conf Uncertainty of Artificial Intelligence"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.850977"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2009.2022705"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2007.04.002"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1198302.1198305"},{"key":"ref37","first-page":"359","article-title":"Collective generation of natural image descriptions","volume":"1","author":"kuznetsova","year":"0","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206492"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2036286"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CYBER.2012.6392580"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072411"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(90)90087-6"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"1985","DOI":"10.1109\/TPAMI.2008.129","article-title":"Video event recognition using kernel methods with multilevel temporal alignment","volume":"30","author":"xu","year":"2008","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70847"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-008-0137-5"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1378704.1378719"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/11880172_15"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.117"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00177"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.455"},{"key":"ref58","first-page":"1218","article-title":"Integrating language and vision to generate natural language descriptions of videos in the wild","author":"thomason","year":"0","journal-title":"Proc 25th Int Conf Comput Linguistics"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/MMUL.2014.29","article-title":"Joint video and text parsing for understanding events and answering queries","volume":"21","author":"tu","year":"2014","journal-title":"IEEE Multimedia"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.118"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2010.2050411"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.329"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33863-2_37"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref3","article-title":"Grounded situation models for situated conversational assistants","author":"mavridis","year":"2007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2007.912817"},{"key":"ref49","first-page":"1250","article-title":"Generating image descriptions using dependency relational patterns","author":"aker","year":"0","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/BF00341922","article-title":"Texture discrimination by Gabor functions","volume":"55","author":"turner","year":"1986","journal-title":"Biol Cybern"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2010.2064299"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.340"},{"key":"ref45","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":"ref48","first-page":"1558","article-title":"Unsupervised alignment of natural language instructions with video segments","author":"naim","year":"0","journal-title":"Proc 28th AAAI Conf Artif Intell"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-2407"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref44","first-page":"1143","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"ordonez","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref127","first-page":"176","article-title":"Better hypothesis testing for statistical machine translation: Controlling for optimizer instability","author":"clark","year":"0","journal-title":"Proc Annu Meeting Assoc Comput Linguist Conf Human Lang Technol"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref124","first-page":"1292","article-title":"Image description using visual dependency representations","volume":"13","author":"elliott","year":"0","journal-title":"Proc Empirical Methods Natural Lang Process"},{"key":"ref73","first-page":"279","article-title":"Natural language descriptions of human behavior from video sequences","author":"tena","year":"0","journal-title":"Proc Annu Conf Artif Intell"},{"key":"ref72","first-page":"595","article-title":"Multimodal neural language models","author":"kiros","year":"0","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-3003"},{"key":"ref71","first-page":"1239","article-title":"How many words is a picture worth? automatic caption generation for news images","author":"feng","year":"0","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2074"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-1602"},{"key":"ref76","article-title":"Deep captioning with multimodal recurrent neural networks (M-RNN)","author":"mao","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00608"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/2324796.2324799"},{"key":"ref75","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":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329409"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.323"},{"key":"ref131","article-title":"Tokyotech+ canon at trecvid 2011","author":"inoue","year":"0","journal-title":"Proc NIST TRECVID Workshop"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298856"},{"key":"ref132","article-title":"Visual recognition of American sign language using hidden Markov models","author":"starner","year":"1995","journal-title":"Proceedings International Workshop on Automatic Face- and Gesture-Recognition"},{"key":"ref79","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":"ref136","first-page":"5758","article-title":"Diverse and accurate image description using a variational auto-encoder with an additive gaussian encoding space","author":"wang","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref135","first-page":"898","article-title":"Contrastive learning for image captioning","author":"dai","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.2200\/S00167ED1V01Y200812ICR002"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247801"},{"key":"ref60","first-page":"2346","article-title":"Jointly modeling deep video and compositional text to bridge vision and language in a unified framework","author":"xu","year":"0","journal-title":"Proc 29th AAAI Conf Artif Intell"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.128"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/0262-8856(88)90001-7"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2017"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/0167-7136(83)90274-3"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2005.07.026"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref65","first-page":"27","article-title":"Describing video contents in natural language","author":"khan","year":"0","journal-title":"Proc Workshop Innovative Hybrid Approaches Process Textual Data"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1103"},{"key":"ref66","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","author":"yang","year":"0","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref142","first-page":"5068","article-title":"Teaching machines to describe images via natural language feedback","author":"ling","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5018-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2011.5771446"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238354"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.339"},{"key":"ref94","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","volume":"37","author":"ioffe","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.117"},{"key":"ref93","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.496"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273577"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref91","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"0","journal-title":"Proceedings of the 32nd Intl Conf on Machine Learning"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.05.080"},{"key":"ref112","article-title":"A comprehensive survey of deep learning for image captioning","author":"hossain","year":"2018","journal-title":"ACM Comput Surv"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4900"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref97","first-page":"2361","article-title":"Review networks for caption generation","volume":"29","author":"yang","year":"2016","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2001.990517"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.79"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011139631724"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806316"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/641007.641073"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247806"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref16","first-page":"453","author":"mavridis","year":"2010","journal-title":"Friends With Faces How Social Networks Can Enhance Face Recognition and Vice Versa"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"ref81","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/34.895972"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref119","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"0","journal-title":"Proc Annu Meeting Assoc Comput Linguist Conf Human Lang Technol"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00138-006-0017-3"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref114","first-page":"1417","article-title":"Multiple instance boosting for object detection","author":"zhang","year":"0","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref113","first-page":"1","article-title":"A survey on deep neural network-based image captioning","author":"liu","year":"2018","journal-title":"Vis Comput"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref120","article-title":"Using descriptive video services to create a large data source for video annotation research","author":"torabi","year":"2015","journal-title":"arXiv 1503 01070"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref123","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Workshop Text Summarization Branches Out"},{"key":"ref85","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"Proc of the Int Conf on Learning Representations (ICLR)"},{"key":"ref86","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"sutskever","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/7433297\/8768200\/8627985-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/8768200\/08627985.pdf?arnumber=8627985","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,11]],"date-time":"2022-09-11T02:09:00Z","timestamp":1662862140000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8627985\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":142,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2019.2892755","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8]]}}}