{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T17:28:43Z","timestamp":1770830923240,"version":"3.50.1"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602405"],"award-info":[{"award-number":["61602405"]}],"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":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"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":["61751209"],"award-info":[{"award-number":["61751209"]}],"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":["61836002"],"award-info":[{"award-number":["61836002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012455","name":"China Knowledge Centre for Engineering Sciences and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012455","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1109\/tcsvt.2019.2957309","type":"journal-article","created":{"date-parts":[[2019,12,3]],"date-time":"2019-12-03T21:05:21Z","timestamp":1575407121000},"page":"4453-4466","source":"Crossref","is-referenced-by-count":14,"title":["Video Dialog via Multi-Grained Convolutional Self-Attention Context Multi-Modal Networks"],"prefix":"10.1109","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3996-8399","authenticated-orcid":false,"given":"Mao","family":"Gu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6121-0384","authenticated-orcid":false,"given":"Zhou","family":"Zhao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3132-5567","authenticated-orcid":false,"given":"Weike","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Deng","family":"Cai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2139-8807","authenticated-orcid":false,"given":"Fei","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/609"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351065"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123364"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2922062"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2890628"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2859820"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref60","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/981732.981751"},{"key":"ref61","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc ACL"},{"key":"ref63","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7287.001.0001"},{"key":"ref27","first-page":"361","article-title":"Multimodal residual learning for visual QA","author":"kim","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref65","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013","journal-title":"arXiv 1301 3781 [cs]"},{"key":"ref66","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2017","journal-title":"arXiv 1412 6980"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/155"},{"key":"ref67","first-page":"4334","article-title":"Leveraging video descriptions to learn video question answering","author":"zeng","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00603"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.446"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref20","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331240"},{"key":"ref24","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 Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2817340"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.11"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.9"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00639"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/513"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref58","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2016","journal-title":"arXiv 1612 08083"},{"key":"ref57","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014","journal-title":"arXiv 1409 1556"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-2117"},{"key":"ref55","article-title":"A structured self-attentive sentence embedding","author":"lin","year":"2017","journal-title":"arXiv 1703 03130"},{"key":"ref54","article-title":"End-to-end audio visual scene-aware dialog using multimodal attention-based video features","author":"hori","year":"2018","journal-title":"arXiv 1806 08409"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_15"},{"key":"ref52","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","author":"chen","year":"2011","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2336697"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2746267"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2307862"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.80"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080655"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref19","article-title":"Simple recurrent units for highly parallelizable recurrence","author":"lei","year":"2017","journal-title":"arXiv 1709 02755"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00637"},{"key":"ref6","first-page":"3719","article-title":"Visual reference resolution using attention memory for visual dialog","author":"seo","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref8","first-page":"2580","article-title":"Answerer in questioner’s mind: Information theoretic approach to goal-oriented visual dialog","author":"lee","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_10"},{"key":"ref49","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 Pattern Recognit"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2902106"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1046"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"ref47","first-page":"314","article-title":"Best of both worlds: Transferring knowledge from discriminative learning to a generative visual dialog model","author":"lu","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref42","first-page":"829","article-title":"Dialog-based language learning","author":"weston","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"3776","article-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","author":"serban","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref44","first-page":"3288","article-title":"Multiresolution recurrent neural networks: An application to dialogue response generation","author":"serban","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref43","first-page":"3295","article-title":"A hierarchical latent variable encoder-decoder model for generating dialogues","author":"serban","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9280452\/08920126.pdf?arnumber=8920126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:39:32Z","timestamp":1651070372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8920126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":68,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2019.2957309","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12]]}}}