{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:14:39Z","timestamp":1765008879420,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0108700"],"award-info":[{"award-number":["2020AAA0108700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3770990","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:06:16Z","timestamp":1765008376000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Joint Fine-grained Disentanglement and Modal-agnostic Fusion Multi-task Framework for Multimodal Sentiment Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5698-5864","authenticated-orcid":false,"given":"Yao","family":"Zheng","sequence":"first","affiliation":[{"name":"Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2247-240X","authenticated-orcid":false,"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8627-4242","authenticated-orcid":false,"given":"Yujun","family":"Wen","sequence":"additional","affiliation":[{"name":"Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1335-0981","authenticated-orcid":false,"given":"Xin","family":"Qi","sequence":"additional","affiliation":[{"name":"Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5721-5692","authenticated-orcid":false,"given":"Pengzhou","family":"Zhang","sequence":"additional","affiliation":[{"name":"Communication University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Sanyuan Chen Chengyi Wang Zhengyang Chen Yu Wu Shujie Liu Zhuo Chen Jinyu Li Naoyuki Kanda Takuya Yoshioka Xiong Xiao et\u00a0al. 2022. Wavlm: Large-scale self-supervised pre-training for full stack speech processing. IEEE J. Sel. Top. Signal Process. 16 6 (2022) 1505\u20131518.","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"e_1_3_3_1_3_2","unstructured":"Weichen Dai Xingyu Li Pengbo Hu Zeyu Wang Ji Qi Jianlin Peng and Yi Zhou. 2024. MInD: Improving Multimodal Sentiment Analysis via Multimodal Information Disentanglement. CoRR (2024)."},{"key":"e_1_3_3_1_4_2","first-page":"4171","volume-title":"NAACL-HLT 2019","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL-HLT 2019. 4171\u20134186."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"AV Geetha T Mala D Priyanka and E Uma. 2024. Multimodal Emotion Recognition with deep learning: advancements challenges and future directions. Inf. Fusion 105 (2024) 102218.","DOI":"10.1016\/j.inffus.2023.102218"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479919"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Zuhe Li Qingbing Guo Yushan Pan Weiping Ding Jun Yu Yazhou Zhang Weihua Liu Haoran Chen Hao Wang and Ying Xie. 2023. Multi-level correlation mining framework with self-supervised label generation for multimodal sentiment analysis. Inf. Fusion 99 (2023) 101891.","DOI":"10.1016\/j.inffus.2023.101891"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"crossref","unstructured":"Qiang Lu Xia Sun Zhizezhang Gao Yunfei Long Jun Feng and Hao Zhang. 2024. Coordinated-joint translation fusion framework with sentiment-interactive graph convolutional networks for multimodal sentiment analysis. Inf. Process. Manage. 61 1 (2024) 103538.","DOI":"10.1016\/j.ipm.2023.103538"},{"key":"e_1_3_3_1_13_2","first-page":"8748","volume-title":"Proc. ICLR 2021","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual models from natural language supervision. In Proc. ICLR 2021. PmLR, 8748\u20138763."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447667"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Licai Sun Zheng Lian Bin Liu and Jianhua Tao. 2023. Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis. IEEE Trans. Affect. Comput. 15 1 (2023) 309\u2013325.","DOI":"10.1109\/TAFFC.2023.3274829"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"e_1_3_3_1_19_2","volume-title":"Proc. ICLR 2019","author":"Tsai Yao-Hung\u00a0Hubert","year":"2019","unstructured":"Yao-Hung\u00a0Hubert Tsai, Paul\u00a0Pu Liang, Amir Zadeh, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Learning Factorized Multimodal Representations. In Proc. ICLR 2019."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Chenchen Wang Qiang Zhang Jing Dong Hui Fang Gerald Schaefer Rui Liu and Pengfei Yi. 2025. A sequential mixing fusion network for enhanced feature representations in multimodal sentiment analysis. Knowledge-Based Syst. (2025) 113638.","DOI":"10.1016\/j.knosys.2025.113638"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Lan Wang Junjie Peng Cangzhi Zheng Tong Zhao and Li\u2019an Zhu. 2024. A cross modal hierarchical fusion multimodal sentiment analysis method based on multi-task learning. Inf. Process. Manage. 61 3 (2024) 103675.","DOI":"10.1016\/j.ipm.2024.103675"},{"key":"e_1_3_3_1_22_2","unstructured":"Yaoting Wang Yuanchao Li Peter Bell and Catherine Lai. 2023. Cross-attention is not enough: Incongruity-aware multimodal sentiment analysis and emotion recognition. CoRR (2023)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Amir Zadeh Minghai Chen Soujanya Poria Erik Cambria and Louis-Philippe Morency. 2017. Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1707.07250 (2017).","DOI":"10.18653\/v1\/D17-1115"},{"key":"e_1_3_3_1_26_2","unstructured":"Amir Zadeh Rowan Zellers Eli Pincus and Louis-Philippe Morency. 2016. Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1606.06259 (2016)."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Yufei Zeng Zhixin Li Zhenjun Tang Zhenbin Chen and Huifang Ma. 2023. Heterogeneous graph convolution based on in-domain self-supervision for multimodal sentiment analysis. Expert Syst. Appl. 213 (2023) 119240.","DOI":"10.1016\/j.eswa.2022.119240"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Ying Zeng Wenjun Yan Sijie Mai and Haifeng Hu. 2024. Disentanglement translation network for multimodal sentiment analysis. Inf. Fusion 102 (2024) 102031.","DOI":"10.1016\/j.inffus.2023.102031"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"crossref","unstructured":"Huanxiang Zhang Junjie Peng and Zesu Cai. 2025. Multimodal sentiment analysis with text-augmented cross-modal feature interaction attention network. Appl. Soft Comput. 175 (2025) 113078.","DOI":"10.1016\/j.asoc.2025.113078"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"crossref","unstructured":"Ying Zhou Xuefeng Liang Han Chen Yin Zhao Xin Chen and Lida Yu. 2025. Triple disentangled representation learning for multimodal affective analysis. Inf. Fusion 114 (2025) 102663.","DOI":"10.1016\/j.inffus.2024.102663"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Linan Zhu Hongyan Zhao Zhechao Zhu Chenwei Zhang and Xiangjie Kong. 2025. Multimodal sentiment analysis with unimodal label generation and modality decomposition. Inf. Fusion 116 (2025) 102787.","DOI":"10.1016\/j.inffus.2024.102787"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611974"}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3770990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:11:16Z","timestamp":1765008676000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3770990"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":32,"alternative-id":["10.1145\/3743093.3770990","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3770990","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}