{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:13:36Z","timestamp":1784178816760,"version":"3.55.0"},"reference-count":76,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076176"],"award-info":[{"award-number":["62076176"]}],"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":["62206193"],"award-info":[{"award-number":["62206193"]}],"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":["62376178"],"award-info":[{"award-number":["62376178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3543080","type":"journal-article","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T13:36:16Z","timestamp":1739799376000},"page":"4924-4935","source":"Crossref","is-referenced-by-count":6,"title":["Enhanced Generative Framework With LLMs for Multimodal Emotion-Cause Pair Extraction in Conversations"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6183-8096","authenticated-orcid":false,"given":"Xincheng","family":"Ju","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, University of Soochow at Suzhou, Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8948-2856","authenticated-orcid":false,"given":"Dong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Soochow at Suzhou, Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7829-6348","authenticated-orcid":false,"given":"Junhui","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Soochow at Suzhou, Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoushan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Soochow at Suzhou, Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7887-5099","authenticated-orcid":false,"given":"Guodong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, University of Soochow at Suzhou, Suzhou, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.342"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.289"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.17"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.290"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3102194"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3089837"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.358"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-021-09925-7"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/584"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26641"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102753"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3226559"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.288"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3319990"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-1409-x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107965"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.240"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3558548"},{"key":"ref19","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548306"},{"key":"ref22","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"CoRR"},{"key":"ref23","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1096"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1170"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3216551"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01599"},{"key":"ref32","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Alayrac","year":"2022"},{"key":"ref33","first-page":"23318","article-title":"OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Wang","year":"2022"},{"key":"ref34","article-title":"Coca: Contrastive captioners are image-text foundation models","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref35","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Liu","year":"2023"},{"key":"ref36","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":"ref37","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023","journal-title":"CoRR"},{"key":"ref38","first-page":"2659","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Narasimhan","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/179"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2754246"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2629489"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1147"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1470"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013027"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/554"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i7.16792"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"key":"ref50","volume-title":"The Nature of Emotion: Fundamental Questions","author":"Ekman","year":"1994"},{"key":"ref51","article-title":"DailyDialog: A manually labelled multi-turn dialogue dataset","author":"Li","year":"2017"},{"key":"ref52","article-title":"Emotionlines: An emotion corpus of multi-party conversations","author":"Chen","year":"2018"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238314"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3267295"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.10.009"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.01.005"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3243463"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110285"},{"key":"ref59","first-page":"45","article-title":"A text-driven rule-based system for emotion cause detection","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Lee","year":"2010"},{"key":"ref60","first-page":"179","article-title":"Emotion cause detection with linguistic constructions","volume-title":"Proc. 23rd Int. Conf. Computat. Linguistics","author":"Chen","year":"2010"},{"key":"ref61","first-page":"153","article-title":"Emocause: An easy-adaptable approach to extract emotion cause contexts","volume-title":"Proc. 2nd Workshop Computat. Approaches Subjectivity Sentiment Anal.","author":"Russo","year":"2011"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-05140-z"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3254166"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref65","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford","year":"2021"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20215"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"ref68","article-title":"UNIFIED-IO: A unified model for vision, language, and multi-modal tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lu","year":"2023"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413949"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.semeval-1.277"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.260"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3223444"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"162","author":"Li","year":"2022"},{"key":"ref76","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10891643.pdf?arnumber=10891643","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T04:24:48Z","timestamp":1756355088000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10891643\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3543080","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}