{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:47:52Z","timestamp":1765039672793,"version":"3.37.3"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0162101"],"award-info":[{"award-number":["2022ZD0162101"]}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["21511101100"],"award-info":[{"award-number":["21511101100"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012656","name":"Shanghai Key Laboratory of Digital Media Processing and Transmission","doi-asserted-by":"publisher","award":["STCSM 22DZ2229005"],"award-info":[{"award-number":["STCSM 22DZ2229005"]}],"id":[{"id":"10.13039\/501100012656","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":[[2024]]},"DOI":"10.1109\/taslp.2023.3284511","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T17:27:13Z","timestamp":1686331633000},"page":"753-764","source":"Crossref","is-referenced-by-count":9,"title":["DialogMCF: Multimodal Context Flow for Audio Visual Scene-Aware Dialog"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4599-1170","authenticated-orcid":false,"given":"Zhe","family":"Chen","sequence":"first","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3271-9544","authenticated-orcid":false,"given":"Hongcheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9500-081X","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Cooperative Medianet Innovation Center, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00774"},{"key":"ref2","article-title":"CMU Sinbads submission for the DSTC7 AVSD challenge","volume-title":"Proc. DSTC7 AAAI2019 Workshop","volume":"6","author":"Sanabria","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065823"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00693"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746481"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"issue":"8","key":"ref7","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref8","article-title":"Investigation on transformer-based multi-modal fusion for audio-visual scene-aware dialog","volume-title":"Proc. DSTC10 AAAI2022 Workshop","author":"Huang","year":"2022"},{"article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","year":"2020","author":"Luo","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"article-title":"Audio visual scene-aware dialog generation with transformer-based video representations","year":"2022","author":"Yamazaki","key":"ref11"},{"key":"ref12","article-title":"Interpretable multimodal dialogue system with natural language-based multimodal integration","volume-title":"Proc. DSTC10 AAAI2022 Workshop","author":"Heo","year":"2022"},{"key":"ref13","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Vaswani","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9883"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17527"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.11"},{"key":"ref18","article-title":"Overview of audio visual scene-aware dialog with reasoning track for natural language generation in DSTC10","volume-title":"Proc. DSTC10 AAAI2022 Workshop","author":"Hori","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101068"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3078368"},{"key":"ref21","article-title":"Distilling the knowledge in a neural network","volume-title":"Proc. Neural Inf. Process. Syst. Deep Learn. Representation Learn. Workshop","author":"Hinton","year":"2014"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3143"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"article-title":"A CLIP-enhanced method for video-language understanding","year":"2021","author":"Li","key":"ref24"},{"key":"ref25","first-page":"2440","article-title":"End-to-end memory networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Sukhbaatar","year":"2015"},{"key":"ref26","article-title":"Memory networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Weston","year":"2015"},{"key":"ref27","first-page":"1378","article-title":"Ask me anything: Dynamic memory networks for natural language processing","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","volume":"48","author":"Kumar","year":"2016"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1136"},{"key":"ref29","article-title":"Global-to-local memory pointer networks for task-oriented dialogue","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2019"},{"key":"ref30","article-title":"Entropy-enhanced multimodal attention model for scene-aware dialogue generation","volume-title":"Proc. DSTC7 AAAI2019 Workshop","author":"Lin","year":"2019"},{"key":"ref31","article-title":"Audio visual scene-aware dialog system using dynamic memory networks","volume-title":"Proc. DSTC8 AAAI2020 Workshop","author":"Xie","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/548"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.321"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_10"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01007"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01757"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00008"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00647"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00682"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref43","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee","year":"2005"},{"key":"ref44","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682583"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref48","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2018"},{"key":"ref49","article-title":"From FiLM to video: Multi-turn question answering with multi-modal context","volume-title":"Proc. DSTC7 AAAI2019 Workshop","author":"Nguyen","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.247"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.145"},{"article-title":"Multi-step joint-modality attention network for scene-aware dialogue system","year":"2020","author":"Chu","key":"ref52"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16273"},{"article-title":"DSTC8-AVSD: Multimodal semantic transformer network with retrieval style word generator","year":"2020","author":"Lee","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16231"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10147255.pdf?arnumber=10147255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T02:23:17Z","timestamp":1705026197000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10147255\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3284511","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"type":"print","value":"2329-9290"},{"type":"electronic","value":"2329-9304"}],"subject":[],"published":{"date-parts":[[2024]]}}}