{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T13:20:20Z","timestamp":1780579220657,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T00:00:00Z","timestamp":1793059200000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Science Foundation","award":["2339707"],"award-info":[{"award-number":["2339707"]}]},{"name":"ILLUM FONDEN","award":["50296"],"award-info":[{"award-number":["50296"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754788","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:27:39Z","timestamp":1761377259000},"page":"2362-2371","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["PgM: Partitioner Guided Modal Learning Framework"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8364-3076","authenticated-orcid":false,"given":"Guimin","family":"Hu","sequence":"first","affiliation":[{"name":"Guangdong University of Technology, Guangzhou, China and University of Copenhagen, Copenhagen, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9526-1323","authenticated-orcid":false,"given":"Yi","family":"Xin","sequence":"additional","affiliation":[{"name":"Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1251-8504","authenticated-orcid":false,"given":"Lijie","family":"Hu","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4530-5516","authenticated-orcid":false,"given":"Zhihong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6437-0463","authenticated-orcid":false,"given":"Hasti","family":"Seifi","sequence":"additional","affiliation":[{"name":"Arizona State University, Tempe, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 29th International Conference on Computational Linguistics. 6955--6965","author":"Chen Shunjie","year":"2022","unstructured":"Shunjie Chen, Xiaochuan Shi, Jingye Li, Shengqiong Wu, Hao Fei, Fei Li, and Donghong Ji. 2022. Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction. In Proceedings of the 29th International Conference on Computational Linguistics. 6955--6965."},{"key":"e_1_3_2_1_3_1","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. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_4_1","volume-title":"On Uni-Modal Feature Learning in Supervised Multi-Modal Learning. In International Conference on Machine Learning, ICML 2023","volume":"8656","author":"Du Chenzhuang","year":"2023","unstructured":"Chenzhuang Du, Jiaye Teng, Tingle Li, Yichen Liu, Tianyuan Yuan, Yue Wang, Yang Yuan, and Hang Zhao. 2023. On Uni-Modal Feature Learning in Supervised Multi-Modal Learning. In International Conference on Machine Learning, ICML 2023, 23--29 July 2023, Honolulu, Hawaii, USA (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 8632--8656. https:\/\/proceedings.mlr.press\/v202\/du23e.html"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.21437\/INTERSPEECH.2021--698"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2023.3237375"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"e_1_3_2_1_9_1","volume-title":"HapticLLaMA: A Multimodal Sensory Language Model for Haptic Captioning. arXiv preprint arXiv:2508.06475","author":"Hu Guimin","year":"2025","unstructured":"Guimin Hu, Daniel Hershcovich, and Hasti Seifi. 2025. HapticLLaMA: A Multimodal Sensory Language Model for Haptic Captioning. arXiv preprint arXiv:2508.06475 (2025)."},{"key":"e_1_3_2_1_10_1","volume-title":"UniMSE: Towards unified multimodal sentiment analysis and emotion recognition. arXiv preprint arXiv:2211.11256","author":"Hu Guimin","year":"2022","unstructured":"Guimin Hu, Ting-En Lin, Yi Zhao, Guangming Lu, Yuchuan Wu, and Yongbin Li. 2022. UniMSE: Towards unified multimodal sentiment analysis and emotion recognition. arXiv preprint arXiv:2211.11256 (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Unimeec: Towards unified multimodal emotion recognition and emotion cause. arXiv preprint arXiv:2404.00403","author":"Hu Guimin","year":"2024","unstructured":"Guimin Hu, Zhihong Zhu, Daniel Hershcovich, Lijie Hu, Hasti Seifi, and Jiayuan Xie. 2024. Unimeec: Towards unified multimodal emotion recognition and emotion cause. arXiv preprint arXiv:2404.00403 (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","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). In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6--14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and JenniferWortman Vaughan (Eds.). 10944--10956. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/5aa3405a3f865c10f420a4a7b55cbff3-Abstract.html"},{"key":"e_1_3_2_1_13_1","volume-title":"International Conference on Machine Learning, ICML 2022","volume":"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, ICML 2022, 17--23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 9226--9259. https:\/\/proceedings.mlr.press\/v162\/huang22e.html"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00740"},{"key":"e_1_3_2_1_15_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_17_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems 34","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems 34 (2021), 9694--9705."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1063"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689092.3689959"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2207.00056"},{"key":"e_1_3_2_1_21_1","volume-title":"MSENA: 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. MSENA: 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":"10.1109\/CVPR.2019.00713"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19--1050"},{"key":"e_1_3_2_1_24_1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res. 21 (2020), 140:1--140:67. http:\/\/jmlr.org\/papers\/v21\/20-074.html","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"e_1_3_2_1_26_1","volume-title":"Ordered neurons: Integrating tree structures into recurrent neural networks. arXiv preprint arXiv:1810.09536","author":"Shen Yikang","year":"2018","unstructured":"Yikang Shen, Shawn Tan, Alessandro Sordoni, and Aaron Courville. 2018. Ordered neurons: Integrating tree structures into recurrent neural networks. arXiv preprint arXiv:1810.09536 (2018)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019","volume":"6569","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. 2019. Multimodal Transformer for Unaligned Multimodal Language Sequences. In Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, Florence, Italy, July 28- August 2, 2019, Volume 1: Long Papers, Anna Korhonen, David R. Traum, and Llu\u00eds M\u00e0rquez (Eds.). Association for Computational Linguistics, 6558--6569. doi:10. 18653\/v1\/p19--1656"},{"key":"e_1_3_2_1_29_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2015.7169757"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34745"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.17"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V36I8"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING","author":"Zhu Zhihong","year":"2024","unstructured":"Zhihong Zhu, Xuxin Cheng, Guimin Hu, Yaowei Li, Zhiqi Huang, and Yuexian Zou. 2024. Towards Multi-modal Sarcasm Detection via Disentangled Multigrained Multi-modal Distilling. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 16581--16591."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/739"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754788","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:00:11Z","timestamp":1765342811000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754788"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":38,"alternative-id":["10.1145\/3746027.3754788","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754788","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}