{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:37:04Z","timestamp":1774312624779,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Project for New Generation of AI","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61802053"],"award-info":[{"award-number":["61802053"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772436"],"award-info":[{"award-number":["61772436"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772118"],"award-info":[{"award-number":["61772118"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806044"],"award-info":[{"award-number":["61806044"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2020YJ0037"],"award-info":[{"award-number":["2020YJ0037"]}]},{"name":"Sichuan Science and Technology Program","award":["2020YJ0207"],"award-info":[{"award-number":["2020YJ0207"]}]},{"name":"Foundation for Department of Transportation of Henan Province","award":["2019J-2-2"],"award-info":[{"award-number":["2019J-2-2"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2682019CX62"],"award-info":[{"award-number":["2682019CX62"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3002667","type":"journal-article","created":{"date-parts":[[2020,6,15]],"date-time":"2020-06-15T22:11:15Z","timestamp":1592259075000},"page":"1744-1756","source":"Crossref","is-referenced-by-count":22,"title":["Adversarial Multimodal Network for Movie Story Question Answering"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4083-5155","authenticated-orcid":false,"given":"Zhaoquan","family":"Yuan","sequence":"first","affiliation":[]},{"given":"Siyuan","family":"Sun","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0723-4016","authenticated-orcid":false,"given":"Lixin","family":"Duan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9789-7632","authenticated-orcid":false,"given":"Changsheng","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8322-8558","authenticated-orcid":false,"given":"Xiao","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1347"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852087"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref32","article-title":"Survey of recent advances in visual question answering","author":"pandhre","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref30","first-page":"1682","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1181"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.12"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/280"},{"key":"ref27","first-page":"2440","article-title":"End-to-end memory networks","author":"sukhbaatar","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref29","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2723841"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"ref24","first-page":"7380","article-title":"Movie question answering: Remembering the textual cues for layered visual contents","author":"wang","year":"0","journal-title":"Proc Thirty-Second AAAI Conf Artif Intell"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00853"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.80"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1215"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/576"},{"key":"ref59","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"0","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Human Lang Technol"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2931534"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref56","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref55","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126695"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271765"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1801"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00438"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350993"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350925"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350971"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350969"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351065"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2940677"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240513"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.312"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/513"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2749160"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2855081"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2796248"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2760101"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2869276"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1414"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2896516"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/385"},{"key":"ref45","first-page":"1218","article-title":"Ask no more: Deciding when to guess in referential visual dialogue","author":"shekhar","year":"0","journal-title":"Proc Twenty-Seventh Int Conf Comput Linguistics"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301395"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5826"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00385"},{"key":"ref44","first-page":"6097","article-title":"FlipDial: A generative model for two-way visual dialogue","author":"massiceti","year":"0","journal-title":"Proc IEEE Conf Comput Vision Pattern Recognit"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/144"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09117168.pdf?arnumber=9117168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:33Z","timestamp":1652194293000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9117168\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3002667","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}