{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:44:05Z","timestamp":1781585045133,"version":"3.54.5"},"reference-count":60,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3591447","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T18:06:50Z","timestamp":1753207610000},"page":"121048-121060","source":"Crossref","is-referenced-by-count":6,"title":["DialogueMLLM: Transforming Multimodal Emotion Recognition in Conversation Through Instruction-Tuned MLLM"],"prefix":"10.1109","volume":"13","author":[{"given":"Yuanyuan","family":"Sun","sequence":"first","affiliation":[{"name":"Central China Normal University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5876-788X","authenticated-orcid":false,"given":"Ting","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref2","article-title":"A comprehensive survey on multi-modal conversational emotion recognition with deep learning","author":"Shou","year":"2023","journal-title":"arXiv:2312.05735"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.824"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.732"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.861"},{"key":"ref6","article-title":"Efficient multimodal large language models: A survey","author":"Jin","year":"2024","journal-title":"arXiv:2405.10739"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.229"},{"key":"ref11","article-title":"EmoBERTa: Speaker-aware emotion recognition in conversation with RoBERTa","author":"Kim","year":"2021","journal-title":"arXiv:2108.12009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3714410"},{"key":"ref13","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref14","volume-title":"Vicuna: An Open-source Chatbot Impressing GPT-4 With 90%* ChatGPT Quality","author":"Chiang","year":"2023"},{"key":"ref15","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref16","article-title":"DeepSeek LLM: Scaling open-source language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv:2401.02954"},{"key":"ref17","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref18","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","first-page":"36637","article-title":"The learnability of in-context learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wies"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-7962-2_30"},{"key":"ref22","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"},{"key":"ref23","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref24","first-page":"11","article-title":"PandaGPT: One model to instruction-follow them all","volume-title":"Proc. 1st Workshop Taming Large Lang. Models","author":"Su"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref26","first-page":"121475","article-title":"CogVLM: Visual expert for pretrained language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref28","article-title":"PLLaVA: Parameter-free LLaVA extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv:2404.16994"},{"key":"ref29","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref31","article-title":"ClinicalGPT: Large language models finetuned with diverse medical data and comprehensive evaluation","author":"Wang","year":"2023","journal-title":"arXiv:2306.09968"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.clsr.2023.105864"},{"key":"ref33","article-title":"The ultimate guide to fine-tuning LLMs from basics to breakthroughs: An exhaustive review of technologies, research, best practices, applied research challenges and opportunities","author":"Balavadhani Parthasarathy","year":"2024","journal-title":"arXiv:2408.13296"},{"key":"ref34","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107751"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.360"},{"key":"ref38","article-title":"Tracing intricate cues in dialogue: Joint graph structure and sentiment dynamics for multimodal emotion recognition","author":"Li","year":"2024","journal-title":"arXiv:2407.21536"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-89202-x"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/app14104199"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888172"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3260635"},{"key":"ref43","article-title":"InstructERC: Reforming emotion recognition in conversation with multi-task retrieval-augmented large language models","author":"Lei","year":"2023","journal-title":"arXiv:2309.11911"},{"key":"ref44","article-title":"ChatGLM: A family of large language models from GLM-130B to GLM-4 all tools","author":"Glm","year":"2024","journal-title":"arXiv:2406.12793"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/e25101440"},{"key":"ref46","first-page":"110805","article-title":"Emotion-llama: Multimodal emotion recognition and reasoning with instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Cheng"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3430850"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/mti6040028"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102218"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1563"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-89758-8"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3558222"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3566059"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3535347"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2025.3568519"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888112"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s13278-025-01428-9"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3711680"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.mcpdig.2024.11.005"},{"key":"ref60","article-title":"Multimodal emotion recognition in conversations: A survey of methods, trends, challenges and prospects","author":"Wu","year":"2025","journal-title":"arXiv:2505.20511"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11088104.pdf?arnumber=11088104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T04:42:41Z","timestamp":1754368961000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11088104\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3591447","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}