{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:01:25Z","timestamp":1740132085024,"version":"3.37.3"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T00:00:00Z","timestamp":1664582400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NeTS-2109982"],"award-info":[{"award-number":["NeTS-2109982"]}],"id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Cisco"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,10,1]]},"DOI":"10.1109\/tpami.2021.3093360","type":"journal-article","created":{"date-parts":[[2021,6,29]],"date-time":"2021-06-29T20:07:12Z","timestamp":1624997232000},"page":"7190-7204","source":"Crossref","is-referenced-by-count":4,"title":["Saying the Unseen: Video Descriptions via Dialog Agents"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0890-9476","authenticated-orcid":false,"given":"Ye","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1680-8253","authenticated-orcid":false,"given":"Yu","family":"Wu","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.524"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref71","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1083-5"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_12"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.345"},{"key":"ref32","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc Text Summarization Branches Out"},{"key":"ref31","first-page":"2584","article-title":"Answerer in questioner’s mind: Information theoretic approach to goal-oriented visual dialog","author":"lee","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(00)80734-5"},{"key":"ref37","first-page":"639","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_20"},{"key":"ref35","first-page":"6097","article-title":"Flipdial: A generative model for two-way visual dialogue.","author":"massiceti","year":"2018","journal-title":"Proc IEEE Conf Comput Vis and Pattern Recog"},{"key":"ref34","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"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref62","first-page":"5758","article-title":"Diverse and accurate image description using a variational auto-encoder with an additive gaussian encoding space","author":"wang","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00947"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.269"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682583"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00639"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967584"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00603"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00138"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240640"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00639"},{"key":"ref69","first-page":"2397","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00971"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.728"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01007"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref24","first-page":"676","article-title":"Dialog-based interactive image retrieval","author":"guo","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01034"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref51","first-page":"3722","article-title":"Visual reference resolution using attention memory for visual dialog","author":"seo","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref58","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1146\/annurev.neuro.23.1.315","article-title":"Mechanisms of visual attention in the human cortex","volume":"23","author":"kastner","year":"2000","journal-title":"Annu Rev Neurosci"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/385"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240563"},{"key":"ref54","first-page":"956","article-title":"Reinforcement learning for spoken dialogue systems","author":"singh","year":"1999","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1646"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.499"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01081"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.10.001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_10"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414296"},{"article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"devlin","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00406"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1648"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref4","first-page":"382","article-title":"Spice: Semantic propositional image caption evaluation","author":"anderson","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref8","first-page":"65","article-title":"Meteor: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Meas Mach Transl Summarization"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00214"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref9","first-page":"1931","article-title":"Variational structured semantic inference for diverse image captioning","author":"chen","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01283"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/1075218.1075231"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref41","first-page":"311","article-title":"Bleu: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1418"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01087"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/9893033\/9468337-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9893033\/09468337.pdf?arnumber=9468337","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,5]],"date-time":"2023-04-05T02:19:04Z","timestamp":1680661144000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9468337\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,1]]},"references-count":82,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3093360","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2022,10,1]]}}}