{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T01:09:16Z","timestamp":1761181756164,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":14,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62173045"],"award-info":[{"award-number":["62173045"]}]},{"name":"Beijing Natural Science Foundation","award":["F2024203115"],"award-info":[{"award-number":["F2024203115"]}]},{"name":"the China Postdoctoral Science Foundation","award":["2024M750255"],"award-info":[{"award-number":["2024M750255"]}]},{"name":"BUPT Excellent Ph.D. Students Foundation","award":["CX2023115"],"award-info":[{"award-number":["CX2023115"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746270.3760219","type":"proceedings-article","created":{"date-parts":[[2025,10,20]],"date-time":"2025-10-20T15:14:09Z","timestamp":1760973249000},"page":"30-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Emo-Synergy: Synergizing Task-Specific and General Experts for Multimodal Emotion Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3076-2949","authenticated-orcid":false,"given":"Ren","family":"Zhang","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7547-5308","authenticated-orcid":false,"given":"Guoliang","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6434-6435","authenticated-orcid":false,"given":"Tianyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2523-5561","authenticated-orcid":false,"given":"Junjun","family":"Zhao","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5427-5345","authenticated-orcid":false,"given":"Bo","family":"Yu","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8067-3648","authenticated-orcid":false,"given":"Zhicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1595-2499","authenticated-orcid":false,"given":"Jianqin","family":"Yin","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning. arXiv preprint arXiv:2504.07198","author":"Chaubey Ashutosh","year":"2025","unstructured":"Ashutosh Chaubey, Xulang Guan, and Mohammad Soleymani. 2025. Face-LLaVA: Facial Expression and Attribute Understanding through Instruction Tuning. arXiv preprint arXiv:2504.07198 (2025)."},{"key":"e_1_3_2_1_2_1","first-page":"110805","article-title":"Emotion-llama: Multimodal emotion recognition and reasoning with instruction tuning","volume":"37","author":"Cheng Zebang","year":"2024","unstructured":"Zebang Cheng, Zhi-Qi Cheng, Jun-Yan He, Kai Wang, Yuxiang Lin, Zheng Lian, Xiaojiang Peng, and Alexander Hauptmann. 2024. Emotion-llama: Multimodal emotion recognition and reasoning with instruction tuning. Advances in Neural Information Processing Systems, Vol. 37 (2024), 110805-110853.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","first-page":"96","article-title":"Utilizing deep learning towards multi-modal bio-sensing and vision-based affective computing","volume":"13","author":"Jung Tzyy-Ping","year":"2019","unstructured":"Tzyy-Ping Jung, Terrence J Sejnowski, et al., 2019. Utilizing deep learning towards multi-modal bio-sensing and vision-based affective computing. IEEE Transactions on Affective Computing, Vol. 13, 1 (2019), 96-107.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1049\/iet-ipr.2017.0499"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3557704"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/e25101440"},{"key":"e_1_3_2_1_7_1","unstructured":"Zheng Lian Rui Liu Kele Xu Bin Liu Xuefei Liu Yazhou Zhang Xin Liu Yong Li Zebang Cheng Haolin Zuo et al. 2025. Mer 2025: When affective computing meets large language models. arXiv preprint arXiv:2504.19423 (2025)."},{"key":"e_1_3_2_1_8_1","unstructured":"Zheng Lian Haiyang Sun Licai Sun Haoyu Chen Lan Chen Hao Gu Zhuofan Wen Shun Chen Siyuan Zhang Hailiang Yao et al. 2024a. OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition. arXiv preprint arXiv:2410.01495 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612836"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689092.3689959"},{"key":"e_1_3_2_1_11_1","volume-title":"AffectGPT: Dataset and framework for explainable multimodal emotion recognition. arXiv preprint arXiv:2407.07653","author":"Lian Zheng","year":"2024","unstructured":"Zheng Lian, Haiyang Sun, Licai Sun, Jiangyan Yi, Bin Liu, and Jianhua Tao. 2024c. AffectGPT: Dataset and framework for explainable multimodal emotion recognition. arXiv preprint arXiv:2407.07653 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Toward machine emotional intelligence: Analysis of affective physiological state","author":"Picard Rosalind W.","year":"2001","unstructured":"Rosalind W. Picard, Elias Vyzas, and Jennifer Healey. 2001. Toward machine emotional intelligence: Analysis of affective physiological state. IEEE transactions on pattern analysis and machine intelligence, Vol. 23, 10 (2001), 1175-1191."},{"key":"e_1_3_2_1_13_1","volume-title":"Emo-llama: Enhancing facial emotion understanding with instruction tuning. arXiv preprint arXiv:2408.11424","author":"Xing Bohao","year":"2024","unstructured":"Bohao Xing, Zitong Yu, Xin Liu, Kaishen Yuan, Qilang Ye, Weicheng Xie, Huanjing Yue, Jingyu Yang, and Heikki K\u00e4lvi\u00e4inen. 2024. Emo-llama: Enhancing facial emotion understanding with instruction tuning. arXiv preprint arXiv:2408.11424 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00089"}],"event":{"name":"MM '25:The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland"},"container-title":["Proceedings of the 3rd International Workshop on Multimodal and Responsible Affective Computing"],"original-title":[],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T17:22:45Z","timestamp":1761153765000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746270.3760219"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,26]]},"references-count":14,"alternative-id":["10.1145\/3746270.3760219","10.1145\/3746270"],"URL":"https:\/\/doi.org\/10.1145\/3746270.3760219","relation":{},"subject":[],"published":{"date-parts":[[2025,10,26]]},"assertion":[{"value":"2025-10-26","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}