{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T15:29:42Z","timestamp":1771514982040,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFA0706203"],"award-info":[{"award-number":["2019YFA0706203"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61932007"],"award-info":[{"award-number":["61932007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AcRF Tier 2 Funding"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3604951","type":"journal-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:31:43Z","timestamp":1756834303000},"page":"8276-8287","source":"Crossref","is-referenced-by-count":8,"title":["Towards Multimodal Emotional Support Conversation Systems"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2953-2657","authenticated-orcid":false,"given":"Yuqi","family":"Chu","sequence":"first","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9973-3305","authenticated-orcid":false,"given":"Lizi","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9376-7045","authenticated-orcid":false,"given":"Zhiyuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-8261","authenticated-orcid":false,"given":"Chong-Wah","family":"Ngo","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1055\/s-0041-1726510"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2196\/44548"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00979-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/wps.20883"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.269"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1534"},{"key":"ref7","first-page":"986","article-title":"Dailydialog: A manually labelled multi-turn dialogue dataset","volume-title":"Proc. 8th Int. Joint Conf. Natural Lang. Process.","author":"Li","year":"2017"},{"key":"ref8","first-page":"1597","article-title":"Emotionlines: An emotion corpus of multi-party conversations","volume-title":"Proc. 11th Int. Conf. Lang. Resour. Eval.","author":"Hsu","year":"2018"},{"key":"ref9","first-page":"44","article-title":"Emotion detection on TV show transcripts with sequence-based convolutional neural networks","volume-title":"Proc. AAAI Workshops","volume":"18","author":"Zahiri","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3260635"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3118881"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3271019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.25"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/600"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.34"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-01981-2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/10503307.2019.1680901"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/0022-0167.32.3.307"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/10412-004"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1037\/h0079733"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.425"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17539"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.224"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.104"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657740"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.606"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238314"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3117062"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3188547"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3333206"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3383123"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11325"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.320"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.70"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21373"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.225"},{"key":"ref40","article-title":"Llama-adapter V2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref41","article-title":"Videochat: Chat-centric video understanding","author":"Li","year":"2023"},{"key":"ref42","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac","year":"2022"},{"key":"ref43","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref44","article-title":"mPLUG-OWL: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref45","first-page":"1","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Zhu","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3109\/09638237.2015.1079308"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.417"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.24"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1037\/h0031619"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/11146689.pdf?arnumber=11146689","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:44:54Z","timestamp":1763059494000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11146689\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3604951","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}