{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T16:05:14Z","timestamp":1778083514688,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"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":[[2024,11,4]]},"DOI":"10.1145\/3678957.3685716","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:35:53Z","timestamp":1730262953000},"page":"339-349","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SMURF: Statistical Modality Uniqueness and Redundancy Factorization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5659-029X","authenticated-orcid":false,"given":"Torsten","family":"W\u00f6rtwein","sequence":"first","affiliation":[{"name":"Educational Testing Service, United States and Language Technologies Institute, Carnegie Mellon University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1086-6639","authenticated-orcid":false,"given":"Nicholas B.","family":"Allen","sequence":"additional","affiliation":[{"name":"Center for Digital Mental Health, University of Oregon, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9393-1116","authenticated-orcid":false,"given":"Jeffrey F.","family":"Cohn","sequence":"additional","affiliation":[{"name":"Psychology, University of Pittsburgh, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6376-7696","authenticated-orcid":false,"given":"Louis-Philippe","family":"Morency","sequence":"additional","affiliation":[{"name":"Language Technologies Institute, Carnegie Mellon University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,4]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Wiley interdisciplinary reviews: computational statistics 2, 3","author":"Alin Aylin","year":"2010","unstructured":"Aylin Alin. 2010. Multicollinearity. Wiley interdisciplinary reviews: computational statistics 2, 3 (2010), 370\u2013374."},{"key":"e_1_3_2_2_2_1","volume-title":"International conference on machine learning. PMLR, 1247\u20131255","author":"Andrew Galen","year":"2013","unstructured":"Galen Andrew, Raman Arora, Jeff Bilmes, and Karen Livescu. 2013. Deep canonical correlation analysis. In International conference on machine learning. PMLR, 1247\u20131255."},{"key":"e_1_3_2_2_3_1","volume-title":"Multimodal machine learning: A survey and taxonomy","author":"Baltru\u0161aitis Tadas","year":"2018","unstructured":"Tadas Baltru\u0161aitis, Chaitanya Ahuja, and Louis-Philippe Morency. 2018. Multimodal machine learning: A survey and taxonomy. IEEE transactions on pattern analysis and machine intelligence 41, 2 (2018), 423\u2013443."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-2466.1973.tb00936.x"},{"key":"e_1_3_2_2_6_1","volume-title":"IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation 42","author":"Busso Carlos","year":"2008","unstructured":"Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Abe Kazemzadeh, Emily Mower, Samuel Kim, Jeannette\u00a0N Chang, Sungbok Lee, and Shrikanth\u00a0S Narayanan. 2008. IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation 42 (2008), 335\u2013359."},{"key":"e_1_3_2_2_7_1","volume-title":"Improving multimodal fusion via mutual dependency maximisation. arXiv preprint arXiv:2109.00922","author":"Colombo Pierre","year":"2021","unstructured":"Pierre Colombo, Emile Chapuis, Matthieu Labeau, and Chloe Clavel. 2021. Improving multimodal fusion via mutual dependency maximisation. arXiv preprint arXiv:2109.00922 (2021)."},{"key":"e_1_3_2_2_8_1","volume-title":"The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing","author":"Eyben Florian","year":"2015","unstructured":"Florian Eyben, Klaus\u00a0R Scherer, Bj\u00f6rn\u00a0W Schuller, Johan Sundberg, Elisabeth Andr\u00e9, Carlos Busso, Laurence\u00a0Y Devillers, Julien Epps, Petri Laukka, Shrikanth\u00a0S Narayanan, 2015. The Geneva minimalistic acoustic parameter set (GeMAPS) for voice research and affective computing. IEEE transactions on affective computing 7, 2 (2015), 190\u2013202."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177013604"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0305004100013517"},{"key":"e_1_3_2_2_13_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.3390\/e24030403"},{"key":"e_1_3_2_2_15_1","volume-title":"Estimating mutual information. Physical review E 69, 6","author":"Kraskov Alexander","year":"2004","unstructured":"Alexander Kraskov, Harald St\u00f6gbauer, and Peter Grassberger. 2004. Estimating mutual information. Physical review E 69, 6 (2004), 066138."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"e_1_3_2_2_17_1","volume-title":"An information decomposition framework. arXiv preprint arXiv:2302.12247","author":"Liang Paul\u00a0Pu","year":"2023","unstructured":"Paul\u00a0Pu Liang, Yun Cheng, Xiang Fan, Chun\u00a0Kai Ling, Suzanne Nie, Richard Chen, Zihao Deng, Faisal Mahmood, Ruslan Salakhutdinov, and Louis-Philippe Morency. 2023. Quantifying & modeling feature interactions: An information decomposition framework. arXiv preprint arXiv:2302.12247 (2023)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428219"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/jcpp.13264"},{"key":"e_1_3_2_2_20_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Advances in Neural Information Processing Systems 32, H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d\u2019Alch\u00e9 Buc, E.\u00a0Fox, and R.\u00a0Garnett (Eds.). Curran Associates, Inc., 8024\u20138035. http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2407898"},{"key":"e_1_3_2_2_22_1","volume-title":"Aaron Van\u00a0den Oord, and Oriol Vinyals","author":"Razavi Ali","year":"2019","unstructured":"Ali Razavi, Aaron Van\u00a0den Oord, and Oriol Vinyals. 2019. Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3243719"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3495002"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2988257.2988258"},{"key":"e_1_3_2_2_26_1","volume-title":"Cues and channels in emotion recognition.Journal of personality and social psychology 51, 4","author":"Wallbott G","year":"1986","unstructured":"Harald\u00a0G Wallbott and Klaus\u00a0R Scherer. 1986. Cues and channels in emotion recognition.Journal of personality and social psychology 51, 4 (1986), 690."},{"key":"e_1_3_2_2_27_1","volume-title":"Learning with Hilbert\u2013Schmidt independence criterion: A review and new perspectives. Knowledge-based systems 234","author":"Wang Tinghua","year":"2021","unstructured":"Tinghua Wang, Xiaolu Dai, and Yuze Liu. 2021. Learning with Hilbert\u2013Schmidt independence criterion: A review and new perspectives. Knowledge-based systems 234 (2021), 107567."},{"key":"e_1_3_2_2_28_1","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"Wang Wenhui","year":"2020","unstructured":"Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in Neural Information Processing Systems 33 (2020), 5776\u20135788.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.344"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3481004"},{"key":"e_1_3_2_2_31_1","volume-title":"Good for misconceived reasons: An empirical revisiting on the need for visual context in multimodal machine translation. arXiv preprint arXiv:2105.14462","author":"Wu Zhiyong","year":"2021","unstructured":"Zhiyong Wu, Lingpeng Kong, Wei Bi, Xiang Li, and Ben Kao. 2021. Good for misconceived reasons: An empirical revisiting on the need for visual context in multimodal machine translation. arXiv preprint arXiv:2105.14462 (2021)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"e_1_3_2_2_33_1","volume-title":"A beginner\u2019s guide to factor analysis: Focusing on exploratory factor analysis. Tutorials in quantitative methods for psychology 9, 2","author":"Yong An\u00a0Gie","year":"2013","unstructured":"An\u00a0Gie Yong, Sean Pearce, 2013. A beginner\u2019s guide to factor analysis: Focusing on exploratory factor analysis. Tutorials in quantitative methods for psychology 9, 2 (2013), 79\u201394."},{"key":"e_1_3_2_2_34_1","volume-title":"Factorized multimodal transformer for multimodal sequential learning. arXiv preprint arXiv:1911.09826","author":"Zadeh Amir","year":"2019","unstructured":"Amir Zadeh, Chengfeng Mao, Kelly Shi, Yiwei Zhang, Paul\u00a0Pu Liang, Soujanya Poria, and Louis-Philippe Morency. 2019. Factorized multimodal transformer for multimodal sequential learning. arXiv preprint arXiv:1911.09826 (2019)."},{"key":"e_1_3_2_2_35_1","volume-title":"Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv preprint arXiv:1606.06259","author":"Zadeh Amir","year":"2016","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:1606.06259 (2016)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119240"},{"key":"e_1_3_2_2_38_1","volume-title":"Learning disentangled representation for multimodal cross-domain sentiment analysis","author":"Zhang Yuhao","year":"2022","unstructured":"Yuhao Zhang, Ying Zhang, Wenya Guo, Xiangrui Cai, and Xiaojie Yuan. 2022. Learning disentangled representation for multimodal cross-domain sentiment analysis. IEEE Transactions on Neural Networks and Learning Systems (2022)."},{"key":"e_1_3_2_2_39_1","volume-title":"Multimodal representations learning based on mutual information maximization and minimization and identity embedding for multimodal sentiment analysis. arXiv preprint arXiv:2201.03969","author":"Zheng Jiahao","year":"2022","unstructured":"Jiahao Zheng, Sen Zhang, Xiaoping Wang, and Zhigang Zeng. 2022. Multimodal representations learning based on mutual information maximization and minimization and identity embedding for multimodal sentiment analysis. arXiv preprint arXiv:2201.03969 (2022)."}],"event":{"name":"ICMI '24: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"San Jose Costa Rica","acronym":"ICMI '24"},"container-title":["International Conference on Multimodel Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678957.3685716","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3678957.3685716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:12Z","timestamp":1750295412000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678957.3685716"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":39,"alternative-id":["10.1145\/3678957.3685716","10.1145\/3678957"],"URL":"https:\/\/doi.org\/10.1145\/3678957.3685716","relation":{},"subject":[],"published":{"date-parts":[[2024,11,4]]},"assertion":[{"value":"2024-11-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}