{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,13]],"date-time":"2026-11-13T02:49:52Z","timestamp":1794538192723,"version":"4.9.1"},"reference-count":47,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1109\/cvpr.2017.475","type":"proceedings-article","created":{"date-parts":[[2017,11,9]],"date-time":"2017-11-09T16:50:33Z","timestamp":1510246233000},"page":"4466-4475","source":"Crossref","is-referenced-by-count":139,"title":["GuessWhat?! Visual Object Discovery through Multi-modal Dialogue"],"prefix":"10.1109","author":[{"given":"Harm","family":"De Vries","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Strub","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarath","family":"Chandar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Pietquin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hugo","family":"Larochelle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Courville","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc of NIPS"},{"key":"ref38","article-title":"Reinforcement Learning for Spoken Dialogue Systems","author":"singh","year":"1999","journal-title":"Proc of NIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref32","article-title":"Software Framework for Topic Modelling with Large Corpora","author":"?eh??ek","year":"2010","journal-title":"Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000343"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.855836"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref36","author":"serban","year":"2015","journal-title":"Hierarchical neural network generative models for movie dialogues"},{"key":"ref35","author":"serban","year":"2015","journal-title":"A survey of available corpora for building data-driven dialogue systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888906000944"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref11","article-title":"Evaluating prerequisite qualities for learning end-to-end dialog systems","author":"dodge","year":"2016","journal-title":"Proceedings of ICL"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2009.03.008"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1422953112"},{"key":"ref14","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref28","author":"mao","year":"2015","journal-title":"Generation and comprehension of unambiguous object descriptions"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/985692.985733"},{"key":"ref27","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 of NIPS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1203"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-4803-7"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1124772.1124782"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143859"},{"key":"ref7","author":"bird","year":"2009","journal-title":"Natural Language Processing With Python"},{"key":"ref2","year":"0","journal-title":"Akinator"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1177\/1745691610393980"},{"key":"ref1","year":"0","journal-title":"20 Questions"},{"key":"ref46","article-title":"Modeling context in referring expressions","author":"yu","year":"2016","journal-title":"Proceedings of ECCV"},{"key":"ref20","author":"kingma","year":"2014","journal-title":"Adam A method for stochastic optimization"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref47","article-title":"Learning deep features for scene recognition using places database","author":"zhou","year":"2014","journal-title":"Proc of NIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/COLI_a_00088"},{"key":"ref42","article-title":"Towards ai-complete question answering: A set of prerequisite toy tasks","author":"weston","year":"2016","journal-title":"Proceedings of ICL"},{"key":"ref24","article-title":"Microsoft coco: Common objects in context","author":"lin","year":"2014","journal-title":"Proc of ECCV"},{"key":"ref41","author":"wen","year":"2016","journal-title":"A Network-based End-to-End Trainable Task-oriented Dialogue System"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"1883","DOI":"10.21437\/Eurospeech.1997-380","article-title":"A stochastic model of computer-human interaction for learning dialogue strategies","volume":"97","author":"levin","year":"1997","journal-title":"Eurospeech"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref26","author":"lu","year":"2016","journal-title":"Hierarchical question-image co-attention for visual question answering"},{"key":"ref43","author":"xu","year":"2015","journal-title":"Show attend and tell Neural image caption generation with visual attention"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1230"}],"event":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Honolulu, HI","start":{"date-parts":[[2017,7,21]]},"end":{"date-parts":[[2017,7,26]]}},"container-title":["2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8097368\/8099483\/08099958.pdf?arnumber=8099958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,6]],"date-time":"2022-08-06T19:26:45Z","timestamp":1659814005000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8099958\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2017.475","relation":{},"subject":[],"published":{"date-parts":[[2017,7]]}}}