{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:07:18Z","timestamp":1776888438679,"version":"3.51.2"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447469","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T14:56:31Z","timestamp":1710773791000},"page":"10516-10520","source":"Crossref","is-referenced-by-count":4,"title":["MSG-BART: Multi-Granularity Scene Graph-Enhanced Encoder-Decoder Language Model for Video-Grounded Dialogue Generation"],"prefix":"10.1109","author":[{"given":"Hongcheng","family":"Liu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pingjie","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Cooperative Medianet Innovation Center"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1012"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16273"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.643"},{"key":"ref6","article-title":"Decoder-only or encoder-decoder? interpreting language model as a regularized encoder-decoder","author":"Fu","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2019.04.002"},{"key":"ref8","article-title":"Videollm: Modeling video sequence with large language models","author":"Chen","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16796"},{"key":"ref10","article-title":"Ord: Object relationship discovery for visual dialogue generation","author":"Wang","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065823"},{"key":"ref12","article-title":"Multimodal transformer with pointer network for the DSTC8 AVSD challenge","volume":"abs\/2002.10695","author":"Le","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref14","article-title":"ActionCLIP: A new paradigm for video action recognition","volume":"abs\/2109.08472","author":"Wang","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01606"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.195"},{"key":"ref18","article-title":"Audio visual scene-aware dialog system using dynamic memory networks","volume-title":"DSTC8 at AAAI2020 workshop","author":"Xie"},{"key":"ref19","article-title":"Investigation on transformer-based multi-modal fusion for audio-visual scene-aware dialog","volume-title":"Proceedings of DSTC10 Workshop at AAAI-2022","author":"Huang"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746481"},{"key":"ref21","article-title":"Audio visual scene-aware dialog generation with transformer-based video representations","volume":"abs\/2202.09979","author":"Yamazaki","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3284511"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2746267"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25983"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447469.pdf?arnumber=10447469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:40:36Z","timestamp":1762195236000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447469","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}