{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:14:39Z","timestamp":1775081679094,"version":"3.50.1"},"reference-count":84,"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":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["108-2221-E-001-012-MY3"],"award-info":[{"award-number":["108-2221-E-001-012-MY3"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["109-2221-E-001-015-"],"award-info":[{"award-number":["109-2221-E-001-015-"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/taslp.2021.3065852","type":"journal-article","created":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T20:57:46Z","timestamp":1615582666000},"page":"2456-2464","source":"Crossref","is-referenced-by-count":4,"title":["End-to-End Recurrent Cross-Modality Attention for Video Dialogue"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4443-070X","authenticated-orcid":false,"given":"Yun-Wei","family":"Chu","sequence":"first","affiliation":[]},{"given":"Kuan-Yen","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Chao-Chun","family":"Hsu","sequence":"additional","affiliation":[]},{"given":"Lun-Wei","family":"Ku","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","article-title":"Ask, attend, and answer: Exploring question-guided spatial attention for visual question answering","author":"xu","year":"2015"},{"key":"ref72","article-title":"Dynamic memory networks for visual and textual question answering","author":"xiong","year":"2016"},{"key":"ref71","article-title":"Are you talking to me? Reasoned visual dialog generation through adversarial learning","author":"wu","year":"2017"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240513"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080655"},{"key":"ref74","article-title":"Show, attend, and tell: Neural image caption generation with visual attention","author":"xu","year":"2015"},{"key":"ref39","article-title":"Knowing when to look: Adaptive attention via a visual sentinel for image captioning","author":"lu","year":"2016"},{"key":"ref75","article-title":"Stacked attention networks for image question answering","author":"yang","year":"2015"},{"key":"ref38","article-title":"Best of both worlds: Transferring knowledge from discriminative learning to a generative visual dialog model","author":"lu","year":"2017"},{"key":"ref78","article-title":"Reactive multi-stage feature fusion for multimodal dialogue modeling","author":"yeh","year":"0"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.503"},{"key":"ref33","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"0","journal-title":"Text Summarization Branches Out"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00642"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1167"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101095"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W15-4640"},{"key":"ref36","article-title":"Video captioning with multi-faceted attention","author":"long","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref34","article-title":"Entropy-enhanced multimodal attention model for scene-aware dialogue generation","author":"lin","year":"0"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984062"},{"key":"ref62","article-title":"Hierarchical LSTMs with adaptive attention for visual captioning","author":"song","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref63","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"n","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_10"},{"key":"ref64","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020346032608"},{"key":"ref65","article-title":"Movieqa: Understanding stories in movies through question-answering","author":"tapaswi","year":"2015"},{"key":"ref66","article-title":"Cider: Consensus-based image description evaluation","author":"vedantam","year":"2014"},{"key":"ref29","article-title":"Context, attention and audio feature explorations for audio visual scene-aware dialog","author":"kumar","year":"2018"},{"key":"ref67","article-title":"A neural conversational model","author":"vinyals","year":"2015"},{"key":"ref68","article-title":"Show and tell: A neural image caption generator","author":"vinyals","year":"2014"},{"key":"ref69","article-title":"Diverse and accurate image description using a variational auto-encoder with an additive gaussian encoding space","author":"wang","year":"2017"},{"key":"ref2","article-title":"Bottom-up and top-down attention for image captioning and VQA","author":"anderson","year":"2017"},{"key":"ref1","article-title":"Audio visual scene-aware dialog (AVSD) challenge at DSTC7","author":"al-amri","year":"2018"},{"key":"ref20","article-title":"Densecap: Fully convolutional localization networks for dense captioning","author":"johnson","year":"2015"},{"key":"ref22","article-title":"Deep visual-semantic alignments for generating image descriptions","author":"karpathy","year":"2014"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1209"},{"key":"ref24","article-title":"Bilinear attention networks","author":"kim","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00260"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/280"},{"key":"ref50","article-title":"Areas of attention for image captioning","author":"pedersoli","year":"2016"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"ref58","article-title":"Visual reference resolution using attention memory for visual dialog","author":"seo","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00214"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01283"},{"key":"ref55","first-page":"3664","article-title":"High-order attention models for visual question answering","author":"schwartz","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.61"},{"key":"ref53","article-title":"Image question answering: A visual semantic embedding model and a new dataset","author":"ren","year":"2015"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref11","article-title":"Visual dialog","author":"das","year":"2016"},{"key":"ref40","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"2016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21236\/ADA623249"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1648"},{"key":"ref14","article-title":"Are you talking to a machine? Dataset and methods for multilingual image question answering","author":"gao","year":"2015"},{"key":"ref15","article-title":"Dynamic fusion with intra- and inter- modality attention flow for visual question answering","author":"gao","year":"2018"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"ref16","article-title":"End-to-end audio visual scene-aware dialog using multimodal attention-based video features","author":"hori","year":"2018"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00603"},{"key":"ref84","article-title":"Visual7w: Grounded question answering in images","author":"zhu","year":"2015"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/512"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984065"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.648"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref3","article-title":"Convolutional image captioning","author":"aneja","year":"2017"},{"key":"ref6","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"0","journal-title":"Proc ACL Workshop Intrinsic Extrinsic Eval Measures Mach Transl Summarization"},{"key":"ref5","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_45"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1117"},{"key":"ref9","article-title":"Learning a recurrent visual representation for image caption generation","author":"chen","year":"2014"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_28"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.80"},{"key":"ref48","article-title":"Hierarchical recurrent neural encoder for video representation with application to captioning","author":"pan","year":"2015"},{"key":"ref47","article-title":"Recursive visual attention in visual dialog","author":"niu","year":"2018"},{"key":"ref42","article-title":"A multi-world approach to question answering about real-world scenes based on uncertain input","author":"malinowski","year":"2014"},{"key":"ref41","article-title":"Co-attending free-form regions and detections with multi-modal multiplicative feature embedding for visual question answering","author":"lu","year":"2017"},{"key":"ref44","article-title":"Flipdial: A generative model for two-way visual dialogue","author":"massiceti","year":"2018"},{"key":"ref43","article-title":"Explain images with multimodal recurrent neural networks","author":"mao","year":"2014"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9289074\/09376964.pdf?arnumber=9376964","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:58Z","timestamp":1652194438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9376964\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/taslp.2021.3065852","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}