{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:05:22Z","timestamp":1779383122317,"version":"3.53.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"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\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-14-1-0679"],"award-info":[{"award-number":["N00014-14-1-0679"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-12-1-0903"],"award-info":[{"award-number":["N00014-12-1-0903"]}],"id":[{"id":"10.13039\/100000006","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":[[2019,5,1]]},"DOI":"10.1109\/tpami.2018.2828437","type":"journal-article","created":{"date-parts":[[2018,4,19]],"date-time":"2018-04-19T18:14:58Z","timestamp":1524161698000},"page":"1242-1256","source":"Crossref","is-referenced-by-count":32,"title":["Visual Dialog"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4718-4316","authenticated-orcid":false,"given":"Abhishek","family":"Das","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satwik","family":"Kottur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khushi","family":"Gupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Avi","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7758-2964","authenticated-orcid":false,"given":"Deshraj","family":"Yadav","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5953-1963","authenticated-orcid":false,"given":"Stefan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9822-8294","authenticated-orcid":false,"given":"Jose M. F.","family":"Moura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3779-6706","authenticated-orcid":false,"given":"Devi","family":"Parikh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhruv","family":"Batra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2675339"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref71","article-title":"A neural conversational model","author":"vinyals","year":"2015"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref76","article-title":"Are you talking to me? reasoned visual dialog generation through adversarial learning","author":"wu","year":"2018","journal-title":"Proc Conf Comput Vis Pattern Recognit"},{"key":"ref77","article-title":"Using artificial intelligence to help blind people ‘see’ facebook","author":"wu","year":"2016"},{"key":"ref39","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref74","article-title":"ELIZA","author":"weizenbaum","year":"0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1230"},{"key":"ref75","article-title":"Towards AI-complete question answering: A set of prerequisite toy tasks","author":"weston","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref79","first-page":"2461","article-title":"Visual madlibs: Fill in the blank image generation and question answering","author":"yu","year":"2015","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939801"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref37","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1127"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/1608974.1608986"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.455"},{"key":"ref60","article-title":"Visual reference resolution using attention memory for visual dialog","author":"seo","year":"2017","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref62","first-page":"3776","article-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","author":"serban","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1056"},{"key":"ref28","article-title":"Sequence to sequence learning with neural networks","author":"ilya sutskever","year":"2014","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref63","first-page":"3295","article-title":"A hierarchical latent variable encoder-decoder model for generating dialogues","author":"serban","year":"2017","journal-title":"AAAI"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref65","doi-asserted-by":"crossref","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref29","first-page":"727","article-title":"Revisiting visual question answering baselines","author":"jabri","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref66","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/385"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref2","year":"0"},{"key":"ref1","year":"0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"3618","DOI":"10.1073\/pnas.1422953112","article-title":"A visual turing test for computer vision systems","volume":"112","author":"geman","year":"2014","journal-title":"Proc Natl Acad Sci United States America"},{"key":"ref21","first-page":"2296","article-title":"Are you talking to a machine? dataset and methods for multilingual image question answering","author":"gao","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref26","first-page":"108","article-title":"Segmentation from natural language expressions","author":"hu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref25","first-page":"1693","article-title":"Teaching machines to read and comprehend","author":"hermann","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref50","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref51","article-title":"Image-grounded conversations: Multimodal context for natural question and response generation","author":"mostafazadeh","year":"2017"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref58","article-title":"Grounding of textual phrases in images by reconstruction","author":"rohrbach","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref57","first-page":"2953","article-title":"Exploring models and data for image question answering","author":"ren","year":"2015","journal-title":"Proc 28th Int Conf Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1090"},{"key":"ref55","first-page":"95","article-title":"Linking people with “their” names using coreference resolution","author":"ramanathan","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/1118053.1118054"},{"key":"ref10","article-title":"Large-scale simple question answering with memory networks","author":"bordes","year":"2015"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/W15-4640","article-title":"The Ubuntu dialogue corpus: A large dataset for research in unstructured multi-turn dialogue systems","author":"lowe","year":"2015","journal-title":"Proc 11th Annu SigDial Meeting Discourse Dialogue"},{"key":"ref11","article-title":"Learning end-to-end goal-oriented dialog","author":"bordes","year":"2017","journal-title":"ICLRE"},{"key":"ref12","article-title":"Evaluating visual conversational agents via cooperative human-ai games","author":"chattopadhyay","year":"2017","journal-title":"Proc 5th AAAI Conf Human Comput Crowdsourcing"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1156"},{"key":"ref14","first-page":"76","article-title":"Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs","author":"danescu-niculescu-mizil","year":"2011","journal-title":"Proc Workshop Cogn Model Comput Linguist"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1092"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref18","article-title":"Evaluating prerequisite qualities for learning end-to-end dialog systems","author":"dodge","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.542"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1091"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1181"},{"key":"ref5","year":"0"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref49","year":"0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref45","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref48","article-title":"Listen, attend, and walk: Neural mapping of navigational instructions to action sequences","author":"mei","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref47","article-title":"FlipDial: A generative model for two-way visual dialogue","author":"massiceti","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref42","article-title":"Deeper LSTM and normalized CNN visual question answering model","author":"lu","year":"2015"},{"key":"ref41","article-title":"Best of both worlds: Transferring knowledge from discriminative learning to a generative visual dialog model","author":"lu","year":"2017","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1097"},{"key":"ref43","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/8679971\/8341743-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8679971\/08341743.pdf?arnumber=8341743","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T21:08:08Z","timestamp":1657746488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8341743\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5,1]]},"references-count":81,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2018.2828437","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,5,1]]}}}