{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:04:14Z","timestamp":1750309454718,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"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\/3678957.3685709","type":"proceedings-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T04:35:53Z","timestamp":1730262953000},"page":"173-181","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Generalization Boost in Bimodal Classification via Data Fusion Trained on Sparse Datasets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0760-1437","authenticated-orcid":false,"given":"Wentao","family":"Yu","sequence":"first","affiliation":[{"name":"Electronic Systems of Medical Engineering, TU Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0678-3053","authenticated-orcid":false,"given":"Dorothea","family":"Kolossa","sequence":"additional","affiliation":[{"name":"Electronic Systems of Medical Engineering, TU Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5007-5355","authenticated-orcid":false,"given":"Robert","family":"Nickel","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Bucknell University, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,4]]},"reference":[{"volume-title":"Linear probability, logit, and probit models. Number\u00a045","author":"Aldrich H","key":"e_1_3_2_1_1_1","unstructured":"John\u00a0H Aldrich and Forrest\u00a0D Nelson. 1984. Linear probability, logit, and probit models. Number\u00a045. Sage."},{"volume-title":"Pattern recognition and machine learning. Vol.\u00a04","author":"Bishop M","key":"e_1_3_2_1_2_1","unstructured":"Christopher\u00a0M Bishop and Nasser\u00a0M Nasrabadi. 2006. Pattern recognition and machine learning. Vol.\u00a04. Springer."},{"key":"e_1_3_2_1_3_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","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, 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","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2172427"},{"key":"e_1_3_2_1_5_1","volume-title":"Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778","author":"Gong Yuan","year":"2021","unstructured":"Yuan Gong, Yu-An Chung, and James Glass. 2021. Ast: Audio spectrogram transformer. arXiv preprint arXiv:2104.01778 (2021)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00102"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865702206150"},{"key":"e_1_3_2_1_8_1","volume-title":"A class of invariant consistent tests for multivariate normality. Communications in statistics-Theory and Methods 19, 10","author":"Henze Norbert","year":"1990","unstructured":"Norbert Henze and Bernd Zirkler. 1990. A class of invariant consistent tests for multivariate normality. Communications in statistics-Theory and Methods 19, 10 (1990), 3595\u20133617."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2784878"},{"key":"e_1_3_2_1_10_1","volume-title":"The hateful memes challenge: Detecting hate speech in multimodal memes. Advances in neural information processing systems 33","author":"Kiela Douwe","year":"2020","unstructured":"Douwe Kiela, Hamed Firooz, Aravind Mohan, Vedanuj Goswami, Amanpreet Singh, Pratik Ringshia, and Davide Testuggine. 2020. The hateful memes challenge: Detecting hate speech in multimodal memes. Advances in neural information processing systems 33 (2020), 2611\u20132624."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3154399"},{"key":"e_1_3_2_1_12_1","volume-title":"On Duality of Exponential and Linear Forgetting. IFAC Proceedings Volumes 29","author":"Kulhav\u1ef3 R","year":"1996","unstructured":"R Kulhav\u1ef3 and FJ Kraus. 1996. On Duality of Exponential and Linear Forgetting. IFAC Proceedings Volumes 29, 1 (1996), 5340\u20135345."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/e25040614"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/79.543975"},{"key":"e_1_3_2_1_15_1","volume-title":"r\/Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detection. arXiv preprint arXiv:1911.03854","author":"Nakamura Kai","year":"2019","unstructured":"Kai Nakamura, Sharon Levy, and William\u00a0Yang Wang. 2019. r\/Fakeddit: A New Multimodal Benchmark Dataset for Fine-grained Fake News Detection. arXiv preprint arXiv:1911.03854 (2019)."},{"key":"e_1_3_2_1_16_1","volume-title":"Proc. ICML. PMLR, 8748\u20138763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, 2021. Learning transferable visual models from natural language supervision. In Proc. ICML. PMLR, 8748\u20138763."},{"key":"e_1_3_2_1_17_1","volume-title":"Robust audio-visual speech recognition under noisy audio-video conditions","author":"Stewart Darryl","year":"2013","unstructured":"Darryl Stewart, Rowan Seymour, Adrian Pass, and Ji Ming. 2013. Robust audio-visual speech recognition under noisy audio-video conditions. IEEE transactions on cybernetics 44, 2 (2013), 175\u2013184."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415085"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415085"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413399"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of De-Factify 2","author":"Yu Wentao","year":"2021","unstructured":"Wentao Yu and Dorothea Kolossa. 2021. wentaorub at Memotion 3: Ensemble learning for multi-modal meme classification. Proceedings of De-Factify 2 (2021)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.23919\/Eusipco47968.2020.9287841"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22155501"}],"event":{"name":"ICMI '24: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","acronym":"ICMI '24","location":"San Jose Costa Rica"},"container-title":["International Conference on Multimodel Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678957.3685709","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3678957.3685709","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\/3678957.3685709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":24,"alternative-id":["10.1145\/3678957.3685709","10.1145\/3678957"],"URL":"https:\/\/doi.org\/10.1145\/3678957.3685709","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"}}]}}