{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T18:25:25Z","timestamp":1780424725046,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":43,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680697","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"5470-5478","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Detached and Interactive Multimodal Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2277-5355","authenticated-orcid":false,"given":"Yunfeng","family":"Fan","sequence":"first","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0983-387X","authenticated-orcid":false,"given":"Wenchao","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7591-5315","authenticated-orcid":false,"given":"Haozhao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5332-1855","authenticated-orcid":false,"given":"Junhong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9831-2202","authenticated-orcid":false,"given":"Song","family":"Guo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Arora Sanjeev","year":"2019","unstructured":"Sanjeev Arora, Nadav Cohen, Wei Hu, and Yuping Luo. 2019. Implicit regularization in deep matrix factorization. Advances in Neural Information Processing Systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_2_1","volume-title":"Crema-d: Crowd-sourced emotional multimodal actors dataset","author":"Cao Houwei","year":"2014","unstructured":"Houwei Cao, David G Cooper, Michael K Keutmann, Ruben C Gur, Ani Nenkova, and Ragini Verma. 2014. Crema-d: Crowd-sourced emotional multimodal actors dataset. IEEE transactions on affective computing, Vol. 5, 4 (2014), 377--390."},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597--1607."},{"key":"e_1_3_2_1_4_1","volume-title":"Improving multi-modal learning with uni-modal teachers. arXiv preprint arXiv:2106.11059","author":"Du Chenzhuang","year":"2021","unstructured":"Chenzhuang Du, Tingle Li, Yichen Liu, Zixin Wen, Tianyu Hua, Yue Wang, and Hang Zhao. 2021. Improving multi-modal learning with uni-modal teachers. arXiv preprint arXiv:2106.11059 (2021)."},{"key":"e_1_3_2_1_5_1","volume-title":"International Conference on Machine Learning. PMLR, 8632--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. PMLR, 8632--8656."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01918"},{"key":"e_1_3_2_1_8_1","volume-title":"Pattern Recognition: 5th Asian Conference, ACPR","author":"Fujimori Naotsuna","year":"2019","unstructured":"Naotsuna Fujimori, Rei Endo, Yoshihiko Kawai, and Takahiro Mochizuki. 2020. Modality-specific learning rate control for multimodal classification. In Pattern Recognition: 5th Asian Conference, ACPR 2019, Auckland, New Zealand, November 26--29, 2019, Revised Selected Papers, Part II 5. Springer, 412--422."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781638281337"},{"key":"e_1_3_2_1_10_1","volume-title":"Contrastive audio-visual masked autoencoder. arXiv preprint arXiv:2210.07839","author":"Gong Yuan","year":"2022","unstructured":"Yuan Gong, Andrew Rouditchenko, Alexander H Liu, David Harwath, Leonid Karlinsky, Hilde Kuehne, and James Glass. 2022. Contrastive audio-visual masked autoencoder. arXiv preprint arXiv:2210.07839 (2022)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"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":"Understanding dimensional collapse in contrastive self-supervised learning. arXiv preprint arXiv:2110.09348","author":"Jing Li","year":"2021","unstructured":"Li Jing, Pascal Vincent, Yann LeCun, and Yuandong Tian. 2021. Understanding dimensional collapse in contrastive self-supervised learning. arXiv preprint arXiv:2110.09348 (2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"Multimodal sentiment analysis: A survey and comparison. Research anthology on implementing sentiment analysis across multiple disciplines","author":"Kaur Ramandeep","year":"2022","unstructured":"Ramandeep Kaur and Sandeep Kautish. 2022. Multimodal sentiment analysis: A survey and comparison. Research anthology on implementing sentiment analysis across multiple disciplines (2022), 1846--1870."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00948"},{"key":"e_1_3_2_1_18_1","volume-title":"Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems","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, Vol. 34 (2021), 9694--9705."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01852"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17047"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00024"},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_24_1","volume-title":"Prototypical networks for few-shot learning. Advances in neural information processing systems","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402 (2012)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3101421"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"e_1_3_2_1_28_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_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00628"},{"key":"e_1_3_2_1_31_1","volume-title":"On modality bias in the TVQA dataset. arXiv preprint arXiv:2012.10210","author":"Winterbottom Thomas","year":"2020","unstructured":"Thomas Winterbottom, Sarah Xiao, Alistair McLean, and Noura Al Moubayed. 2020. On modality bias in the TVQA dataset. arXiv preprint arXiv:2012.10210 (2020)."},{"key":"e_1_3_2_1_32_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_33_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 1912--1920","author":"Wu Zhirong","year":"2015","unstructured":"Zhirong Wu, Shuran Song, Aditya Khosla, Fisher Yu, Linguang Zhang, Xiaoou Tang, and Jianxiong Xiao. 2015. 3d shapenets: A deep representation for volumetric shapes. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1912--1920."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3013234"},{"key":"e_1_3_2_1_35_1","volume-title":"The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation. In The Eleventh International Conference on Learning Representations.","author":"Xue Zihui","year":"2022","unstructured":"Zihui Xue, Zhengqi Gao, Sucheng Ren, and Hang Zhao. 2022. The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_17"},{"key":"e_1_3_2_1_38_1","volume-title":"Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783","author":"Yao Lewei","year":"2021","unstructured":"Lewei Yao, Runhui Huang, Lu Hou, Guansong Lu, Minzhe Niu, Hang Xu, Xiaodan Liang, Zhenguo Li, Xin Jiang, and Chunjing Xu. 2021. Filip: Fine-grained interactive language-image pre-training. arXiv preprint arXiv:2111.07783 (2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00696"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.143"},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 3195--3201","author":"Zhang Qiulin","year":"2021","unstructured":"Qiulin Zhang, Zhuqing Jiang, Qishuo Lu, Zhengxin Zeng, Shang-Hua Gao, and Aidong Men. 2021. Split to be slim: an overlooked redundancy in vanilla convolution. In Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence. 3195--3201."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612468"},{"key":"e_1_3_2_1_43_1","volume-title":"Do llms understand visual anomalies? uncovering llm capabilities in zero-shot anomaly detection. arXiv preprint arXiv:2404.09654","author":"Zhu Jiaqi","year":"2024","unstructured":"Jiaqi Zhu, Shaofeng Cai, Fang Deng, and Junran Wu. 2024. Do llms understand visual anomalies? uncovering llm capabilities in zero-shot anomaly detection. arXiv preprint arXiv:2404.09654 (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 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680697","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680697"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":43,"alternative-id":["10.1145\/3664647.3680697","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680697","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"}}]}}