{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:23:22Z","timestamp":1778693002806,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"name":"Beijing Outstanding Young Scientist Program","award":["No.JWZQ20240101027"],"award-info":[{"award-number":["No.JWZQ20240101027"]}]},{"name":"National Nature Science Foundation of China","award":["No.12071313"],"award-info":[{"award-number":["No.12071313"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733266","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:04Z","timestamp":1750876264000},"page":"1191-1200","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Agent Semantic Aggregation Network for Multimodal Sentiment Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0472-9062","authenticated-orcid":false,"given":"Yue","family":"Su","sequence":"first","affiliation":[{"name":"School of Mathematical Sciences, Capital Normal University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1367-0692","authenticated-orcid":false,"given":"Xuying","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Capital Normal University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680781"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01471"},{"key":"e_1_3_2_1_3_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al. 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.025"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10555-8"},{"key":"e_1_3_2_1_6_1","volume-title":"Jeremy Smith, Ka Lok Man, and Yutao Yue.","author":"Guan Runwei","year":"2024","unstructured":"Runwei Guan, Liye Jia, Fengyufan Yang, Shanliang Yao, Erick Purwanto, Xiaohui Zhu, Eng Gee Lim, Jeremy Smith, Ka Lok Man, and Yutao Yue. 2024. Watervg: Waterway visual grounding based on text-guided vision and mmwave radar. arXiv preprint arXiv:2403.12686 (2024)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"e_1_3_2_1_9_1","volume-title":"Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. arXiv preprint arXiv:2109.00412","author":"Han Wei","year":"2021","unstructured":"Wei Han, Hui Chen, and Soujanya Poria. 2021. Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. arXiv preprint arXiv:2109.00412 (2021)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"e_1_3_2_1_12_1","volume-title":"International conference on machine learning. PMLR, 5156--5165","author":"Katharopoulos Angelos","year":"2020","unstructured":"Angelos Katharopoulos, Apoorv Vyas, Nikolaos Pappas, and Fran\u00e7ois Fleuret. 2020. Transformers are rnns: Fast autoregressive transformers with linear attention. In International conference on machine learning. PMLR, 5156--5165."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. Minneapolis, Minnesota, 2."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01753"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109368"},{"key":"e_1_3_2_1_16_1","volume-title":"International Journal of Computer Vision","author":"Liu Yuanyuan","year":"2024","unstructured":"Yuanyuan Liu, Haoyu Zhang, Yibing Zhan, Zijing Chen, Guanghao Yin, Lin Wei, and Zhe Chen. 2024. Noise-resistant multimodal transformer for emotion recognition. International Journal of Computer Vision (2024), 1--21."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"e_1_3_2_1_19_1","first-page":"21297","article-title":"Soft: Softmax-free transformer with linear complexity","volume":"34","author":"Lu Jiachen","year":"2021","unstructured":"Jiachen Lu, Jinghan Yao, Junge Zhang, Xiatian Zhu, Hang Xu, Weiguo Gao, Chunjing Xu, Tao Xiang, and Li Zhang. 2021. Soft: Softmax-free transformer with linear complexity. Advances in Neural Information Processing Systems, Vol. 34 (2021), 21297--21309.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"e_1_3_2_1_21_1","volume-title":"M-SENA: An integrated platform for multimodal sentiment analysis. arXiv preprint arXiv:2203.12441","author":"Mao Huisheng","year":"2022","unstructured":"Huisheng Mao, Ziqi Yuan, Hua Xu, Wenmeng Yu, Yihe Liu, and Kai Gao. 2022. M-SENA: An integrated platform for multimodal sentiment analysis. arXiv preprint arXiv:2203.12441 (2022)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"e_1_3_2_1_24_1","volume-title":"13th IEEE International Conference on Automatic Face & Gesture Recognition.","author":"Tadas Baltrusaitis","year":"2018","unstructured":"Baltrusaitis Tadas, Zadeh Amir, Lim Yao Chong, and Louis-Morency Philippe. 2018. Openface 2.0: Facial behavior analysis toolkit. In 13th IEEE International Conference on Automatic Face & Gesture Recognition."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the conference. Association for computational linguistics. Meeting","volume":"2019","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019a. Multimodal transformer for unaligned multimodal language sequences. In Proceedings of the conference. Association for computational linguistics. Meeting, Vol. 2019. NIH Public Access, 6558."},{"key":"e_1_3_2_1_26_1","volume-title":"Learning Factorized Multimodal Representations. In International Conference on Learning Representations.","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019b. Learning Factorized Multimodal Representations. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_27_1","article-title":"Visualizing data using t-SNE","volume":"9","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research, Vol. 9, 11 (2008).","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_28_1","volume-title":"Attention is all you need. Advances in neural information processing systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10988-9"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17664"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"e_1_3_2_1_34_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, Zongyang Ma, Wanxiang Che, and Bing Qin. 2024b. Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey. arXiv preprint arXiv:2406.08068 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.135"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108348"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01387"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"e_1_3_2_1_41_1","volume-title":"Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250","author":"Zadeh Amir","year":"2017","unstructured":"Amir Zadeh, Minghai Chen, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency. 2017. Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_2_1_44_1","volume-title":"Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis. In The 2023 Conference on Empirical Methods in Natural Language Processing.","author":"Zhang Haoyu","year":"2023","unstructured":"Haoyu Zhang, Yu Wang, Guanghao Yin, Kejun Liu, Yuanyuan Liu, and Tianshu Yu. 2023. Learning Language-guided Adaptive Hyper-modality Representation for Multimodal Sentiment Analysis. In The 2023 Conference on Empirical Methods in Natural Language Processing."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1108\/IJICC-07-2024-0310"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.02.028"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681527"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:08:40Z","timestamp":1755749320000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733266"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":48,"alternative-id":["10.1145\/3731715.3733266","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733266","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}