{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:33:46Z","timestamp":1776890026622,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2024A1515010112"],"award-info":[{"award-number":["2024A1515010112"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3689092.3689402","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T18:33:17Z","timestamp":1729708397000},"page":"99-103","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Open Vocabulary Emotion Prediction Based on Large Multimodal Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8487-0561","authenticated-orcid":false,"given":"Zixing","family":"Zhang","sequence":"first","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8074-1746","authenticated-orcid":false,"given":"Zhongren","family":"Dong","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5283-6173","authenticated-orcid":false,"given":"Zhiqiang","family":"Gao","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3366-8648","authenticated-orcid":false,"given":"Shihao","family":"Gao","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9393-5532","authenticated-orcid":false,"given":"Donghao","family":"Wang","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5557-824X","authenticated-orcid":false,"given":"Ciqiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5380-0196","authenticated-orcid":false,"given":"Yuhan","family":"Nie","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6286-5868","authenticated-orcid":false,"given":"Huan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Hunan University, Changsha, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_2_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_1_3_1","volume-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919","author":"Chu Yunfei","year":"2023","unstructured":"Yunfei Chu, Jin Xu, Xiaohuan Zhou, Qian Yang, Shiliang Zhang, Zhijie Yan, Chang Zhou, and Jingren Zhou. 2023. Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:2311.07919 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"A survey on in-context learning. arXiv preprint arXiv:2301.00234","author":"Dong Qingxiu","year":"2022","unstructured":"Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu Sun, Jingjing Xu, and Zhifang Sui. 2022. A survey on in-context learning. arXiv preprint arXiv:2301.00234 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models. arXiv preprint arXiv:2407.07895","author":"Li Feng","year":"2024","unstructured":"Feng Li, Renrui Zhang, Hao Zhang, Yuanhan Zhang, Bo Li, Wei Li, Zejun Ma, and Chunyuan Li. 2024. LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models. arXiv preprint arXiv:2407.07895 (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355","author":"Li KunChang","year":"2023","unstructured":"KunChang Li, Yinan He, Yi Wang, Yizhuo Li, Wenhai Wang, Ping Luo, Yali Wang, Limin Wang, and Yu Qiao. 2023. Videochat: Chat-centric video understanding. arXiv preprint arXiv:2305.06355 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition. arXiv preprint arXiv:2404","author":"Lian Zheng","year":"2024","unstructured":"Zheng Lian, Haiyang Sun, Licai Sun, Zhuofan Wen, Siyuan Zhang, Shun Chen, Hao Gu, Jinming Zhao, Ziyang Ma, Xie Chen, et al. 2024. MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition. arXiv preprint arXiv:2404.17113 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Merbench: A unified evaluation benchmark for multimodal emotion recognition. arXiv preprint arXiv:2401.03429","author":"Lian Zheng","year":"2024","unstructured":"Zheng Lian, Licai Sun, Yong Ren, Hao Gu, Haiyang Sun, Lan Chen, Bin Liu, and Jianhua Tao. 2024. Merbench: A unified evaluation benchmark for multimodal emotion recognition. arXiv preprint arXiv:2401.03429 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Explainable multimodal emotion reasoning. arXiv preprint arXiv:2306.15401","author":"Lian Zheng","year":"2023","unstructured":"Zheng Lian, Licai Sun, Mingyu Xu, Haiyang Sun, Ke Xu, Zhuofan Wen, Shun Chen, Bin Liu, and Jianhua Tao. 2023. Explainable multimodal emotion reasoning. arXiv preprint arXiv:2306.15401 (2023)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"e_1_3_2_1_11_1","volume-title":"Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122","author":"Lin Bin","year":"2023","unstructured":"Bin Lin, Bin Zhu, Yang Ye, Munan Ning, Peng Jin, and Li Yuan. 2023. Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255","author":"Lu Pan","year":"2023","unstructured":"Pan Lu, Hritik Bansal, Tony Xia, Jiacheng Liu, Chunyuan Li, Hannaneh Hajishirzi, Hao Cheng, Kai-Wei Chang, Michel Galley, and Jianfeng Gao. 2023. Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts. arXiv preprint arXiv:2310.02255 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Introducing meta llama 3: The most capable openly available llm to date. Meta AI","author":"Meta AI","year":"2024","unstructured":"AI Meta. 2024. Introducing meta llama 3: The most capable openly available llm to date. Meta AI (2024)."},{"key":"e_1_3_2_1_14_1","unstructured":"OpenAI. 2023. GPT-4V(ision) System Card. https:\/\/api.semanticscholar.org\/CorpusID:263218031"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447044"},{"key":"e_1_3_2_1_16_1","volume-title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models. In The Twelfth International Conference on Learning Representations.","author":"Tang Changli","unstructured":"Changli Tang, Wenyi Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, MA Zejun, and Chao Zhang. [n.,d.]. SALMONN: Towards Generic Hearing Abilities for Large Language Models. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_1_17_1","unstructured":"An Yang Baosong Yang Binyuan Hui Bo Zheng Bowen Yu Chang Zhou Chengpeng Li Chengyuan Li Dayiheng Liu Fei Huang et al. 2024. Qwen2 Technical Report. arXiv preprint arXiv:2407.10671 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey. arXiv preprint arXiv:2406","author":"Yang Hao","year":"2024","unstructured":"Hao Yang, Yanyan Zhao, Yang Wu, Shilong Wang, Tian Zheng, Hongbo Zhang, Wanxiang Che, and Bing Qin. 2024. Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey. arXiv preprint arXiv:2406.08068 (2024)."},{"key":"e_1_3_2_1_19_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi et al. 2023. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"e_1_3_2_1_21_1","volume-title":"Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858","author":"Zhang Hang","year":"2023","unstructured":"Hang Zhang, Xin Li, and Lidong Bing. 2023. Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Refashioning emotion recognition modelling: The advent of generalised large models","author":"Zhang Zixing","year":"2024","unstructured":"Zixing Zhang, Liyizhe Peng, Tao Pang, Jing Han, Huan Zhao, and Bj\u00f6rn W Schuller. 2024. Refashioning emotion recognition modelling: The advent of generalised large models. IEEE Transactions on Computational Social Systems (2024)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2nd International Workshop on Multimodal and Responsible Affective Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689092.3689402","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689092.3689402","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:59:44Z","timestamp":1755914384000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689092.3689402"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":22,"alternative-id":["10.1145\/3689092.3689402","10.1145\/3689092"],"URL":"https:\/\/doi.org\/10.1145\/3689092.3689402","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}