{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T09:54:47Z","timestamp":1780653287664,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":46,"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":"VinIF","award":["VINIF.2023.TS147"],"award-info":[{"award-number":["VINIF.2023.TS147"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681648","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"9330-9339","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Ada2I: Enhancing Modality Balance for Multimodal Conversational Emotion Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9675-2105","authenticated-orcid":false,"given":"Cam-Van Thi","family":"Nguyen","sequence":"first","affiliation":[{"name":"VNU University of Engineering and Technology, Hanoi, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7639-129X","authenticated-orcid":false,"given":"The-Son","family":"Le","sequence":"additional","affiliation":[{"name":"VNU University of Engineering and Technology, Hanoi, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7211-2637","authenticated-orcid":false,"given":"Anh-Tuan","family":"Mai","sequence":"additional","affiliation":[{"name":"VNU University of Engineering and Technology, Hanoi, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4621-8956","authenticated-orcid":false,"given":"Duc-Trong","family":"Le","sequence":"additional","affiliation":[{"name":"VNU University of Engineering and Technology, Hanoi, Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_2_1","volume-title":"Multimodal machine learning: A survey and taxonomy","author":"Baltruvsaitis Tadas","year":"2018","unstructured":"Tadas Baltruvsaitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multimodal machine learning: A survey and taxonomy. IEEE transactions on pattern analysis and machine intelligence, Vol. 41, 2 (2018), 423--443."},{"key":"e_1_3_2_1_3_1","volume-title":"IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation","author":"Busso Carlos","year":"2008","unstructured":"Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette N Chang, Sungbok Lee, and Shrikanth S Narayanan. 2008. IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation, Vol. 42, 4 (2008), 335--359."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.challengehml-1.1"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01918"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Devamanyu Hazarika Soujanya Poria Rada Mihalcea Erik Cambria and Roger Zimmermann. 2018. ICON: Interactive Conversational Memory Network for Multimodal Emotion Detection. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing Ellen Riloff David Chiang Julia Hockenmaier and Jun'ichi Tsujii (Eds.). Association for Computational Linguistics Brussels Belgium 2594--2604. https:\/\/doi.org\/10.18653\/v1\/D18--1280","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1193"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Huang Gao","unstructured":"Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. 2017. Densely Connected Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_13_1","first-page":"10944","article-title":"What makes multi-modal learning better than single (provably)","volume":"34","author":"Huang Yu","year":"2021","unstructured":"Yu Huang, Chenzhuang Du, Zihui Xue, Xuanyao Chen, Hang Zhao, and Longbo Huang. 2021. What makes multi-modal learning better than single (provably). Advances in Neural Information Processing Systems, Vol. 34 (2021), 10944--10956.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning. PMLR, 9226--9259","author":"Huang Yu","year":"2022","unstructured":"Yu Huang, Junyang Lin, Chang Zhou, Hongxia Yang, and Longbo Huang. 2022. Modality competition: What makes joint training of multi-modal network fail in deep learning?(provably). In International Conference on Machine Learning. PMLR, 9226--9259."},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Machine Learning. PMLR, 9938--9964","author":"Javaloy Adri\u00e1n","year":"2022","unstructured":"Adri\u00e1n Javaloy, Maryam Meghdadi, and Isabel Valera. 2022. Mitigating modality collapse in multimodal VAEs via impartial optimization. In International Conference on Machine Learning. PMLR, 9938--9964."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.306"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612053"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126427"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"e_1_3_2_1_20_1","volume-title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1).","author":"Liang Paul Pu","year":"2021","unstructured":"Paul Pu Liang, Yiwei Lyu, Xiang Fan, Zetian Wu, Yun Cheng, Jason Wu, Leslie Yufan Chen, Peter Wu, Michelle A Lee, Yuke Zhu, et al. 2021. MultiBench: Multiscale Benchmarks for Multimodal Representation Learning. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 1)."},{"key":"e_1_3_2_1_21_1","volume-title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions. arXiv preprint arXiv:2209.03430","author":"Liang Paul Pu","year":"2022","unstructured":"Paul Pu Liang, Amir Zadeh, and Louis-Philippe Morency. 2022. Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions. arXiv preprint arXiv:2209.03430 (2022)."},{"key":"e_1_3_2_1_22_1","volume-title":"Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing. arXiv preprint arXiv:2402.19298","author":"Lin Xun","year":"2024","unstructured":"Xun Lin, Shuai Wang, Rizhao Cai, Yizhong Liu, Ying Fu, Zitong Yu, Wenzhong Tang, and Alex Kot. 2024. Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing. arXiv preprint arXiv:2402.19298 (2024)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024","author":"Thi Nguyen Cam-Van","year":"2024","unstructured":"Cam-Van Thi Nguyen, Cao-Bach Nguyen, Duc-Trong Le, and Quang-Thuy Ha. 2024. Curriculum Learning Meets Directed Acyclic Graph for Multimodal Emotion Recognition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, Torino, Italia, 4259--4265. https:\/\/aclanthology.org\/2024.lrec-main.380"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"e_1_3_2_1_29_1","volume-title":"wav2vec: Unsupervised pre-training for speech recognition. arXiv preprint arXiv:1904.05862","author":"Schneider Steffen","year":"2019","unstructured":"Steffen Schneider, Alexei Baevski, Ronan Collobert, and Michael Auli. 2019. wav2vec: Unsupervised pre-training for speech recognition. arXiv preprint arXiv:1904.05862 (2019)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/480"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29876"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems. 6000--6010","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. In Proceedings of the 31st International Conference on Neural Information Processing Systems. 6000--6010."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123359"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613846"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_39_1","volume-title":"International Conference on Machine Learning. PMLR, 24043--24055","author":"Wu Nan","year":"2022","unstructured":"Nan Wu, Stanislaw Jastrzebski, Kyunghyun Cho, and Krzysztof J Geras. 2022. Characterizing and overcoming the greedy nature of learning in multi-modal deep neural networks. In International Conference on Machine Learning. PMLR, 24043--24055."},{"key":"e_1_3_2_1_40_1","volume-title":"ICASSP 2023--2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Xu Ruize","unstructured":"Ruize Xu, Ruoxuan Feng, Shi-Xiong Zhang, and Di Hu. 2023. MMCosine: Multi-Modal Cosine Loss Towards Balanced Audio-Visual Fine-Grained Learning. In ICASSP 2023--2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1--5."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413949"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"e_1_3_2_1_43_1","unstructured":"Qingyang Zhang Yake Wei Zongbo Han Huazhu Fu Xi Peng Cheng Deng Qinghua Hu Cai Xu Jie Wen Di Hu et al. 2024. Multimodal fusion on low-quality data: A comprehensive survey. arXiv preprint arXiv:2404.18947 (2024)."},{"key":"e_1_3_2_1_44_1","volume-title":"Tensor ring decomposition. arXiv preprint arXiv:1606.05535","author":"Zhao Qibin","year":"2016","unstructured":"Qibin Zhao, Guoxu Zhou, Shengli Xie, Liqing Zhang, and Andrzej Cichocki. 2016. Tensor ring decomposition. arXiv preprint arXiv:1606.05535 (2016)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00534"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612468"}],"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 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681648","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681648"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":46,"alternative-id":["10.1145\/3664647.3681648","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681648","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"}}]}}