{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T04:22:50Z","timestamp":1776399770434,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T00:00:00Z","timestamp":1667779200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Beijing Academy of Artificial Intelligence(BAAI)"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62173195"],"award-info":[{"award-number":["62173195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003787","name":"Natural Science Foundation of Hebei Province","doi-asserted-by":"publisher","award":["F2022208006"],"award-info":[{"award-number":["F2022208006"]}],"id":[{"id":"10.13039\/501100003787","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,11,7]]},"DOI":"10.1145\/3536221.3556630","type":"proceedings-article","created":{"date-parts":[[2022,11,4]],"date-time":"2022-11-04T15:54:14Z","timestamp":1667577254000},"page":"247-258","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":46,"title":["Make Acoustic and Visual Cues Matter: CH-SIMS v2.0 Dataset and AV-Mixup Consistent Module"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7487-2213","authenticated-orcid":false,"given":"Yihe","family":"Liu","sequence":"first","affiliation":[{"name":"Hebei University of Science and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2397-2163","authenticated-orcid":false,"given":"Ziqi","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6321-4239","authenticated-orcid":false,"given":"Huisheng","family":"Mao","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1959-7949","authenticated-orcid":false,"given":"Zhiyun","family":"Liang","sequence":"additional","affiliation":[{"name":"China Agricultural University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2109-6684","authenticated-orcid":false,"given":"Wanqiuyue","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing University of Post and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0870-8807","authenticated-orcid":false,"given":"Yuanzhe","family":"Qiu","sequence":"additional","affiliation":[{"name":"Hebei University of Science and Technology, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8791-9957","authenticated-orcid":false,"given":"Tie","family":"Cheng","sequence":"additional","affiliation":[{"name":"Beijing University of Post and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2878-9675","authenticated-orcid":false,"given":"Xiaoteng","family":"Li","sequence":"additional","affiliation":[{"name":"Hebei University of Science and Technology, Shijiazhuang,China, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7401-307X","authenticated-orcid":false,"given":"Hua","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6920-850X","authenticated-orcid":false,"given":"Kai","family":"Gao","sequence":"additional","affiliation":[{"name":"Hebei University of Science and Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2022,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Shahin Amiriparian Artem Sokolov Ilhan Aslan Lukas Christ Maurice Gerczuk Tobias H\u00fcbner Dmitry Lamanov Manuel Milling Sandra Ottl Ilya Poduremennykh 2021. On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era. arXiv preprint arXiv:2104.10121(2021).  Shahin Amiriparian Artem Sokolov Ilhan Aslan Lukas Christ Maurice Gerczuk Tobias H\u00fcbner Dmitry Lamanov Manuel Milling Sandra Ottl Ilya Poduremennykh 2021. On the Impact of Word Error Rate on Acoustic-Linguistic Speech Emotion Recognition: An Update for the Deep Learning Era. arXiv preprint arXiv:2104.10121(2021)."},{"key":"e_1_3_2_1_2_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. 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_1_3_1","volume-title":"IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation 42, 4","author":"Busso Carlos","year":"2008","unstructured":"Carlos Busso , Murtaza Bulut , Chi-Chun Lee , Abe Kazemzadeh , Emily Mower , Samuel Kim , Jeannette\u00a0 N Chang , Sungbok Lee , and Shrikanth\u00a0 S Narayanan . 2008 . IEMOCAP: Interactive emotional dyadic motion capture database. Language resources and evaluation 42, 4 (2008), 335\u2013359. 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, 4 (2008), 335\u2013359."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"J. Chen Z. Yang and D. Yang. 2020. MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification. (2020).  J. Chen Z. Yang and D. Yang. 2020. MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification. (2020).","DOI":"10.18653\/v1\/2020.acl-main.194"},{"key":"e_1_3_2_1_5_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018).","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805(2018)."},{"key":"e_1_3_2_1_6_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\u00a0 R Scherer , Bj\u00f6rn\u00a0 W Schuller , Johan Sundberg , Elisabeth Andr\u00e9 , Carlos Busso , Laurence\u00a0 Y Devillers , Julien Epps , Petri Laukka , Shrikanth\u00a0 S 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. 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_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"e_1_3_2_1_8_1","unstructured":"Deepanway Ghosal Navonil Majumder Rada Mihalcea and Soujanya Poria. 2020. Utterance-level dialogue understanding: An empirical study. arXiv preprint arXiv:2009.13902(2020).  Deepanway Ghosal Navonil Majumder Rada Mihalcea and Soujanya Poria. 2020. Utterance-level dialogue understanding: An empirical study. arXiv preprint arXiv:2009.13902(2020)."},{"key":"e_1_3_2_1_9_1","unstructured":"H. Guo Y. Mao and R. Zhang. 2019. Augmenting Data with Mixup for Sentence Classification: An Empirical Study. (2019).  H. Guo Y. Mao and R. Zhang. 2019. Augmenting Data with Mixup for Sentence Classification: An Empirical Study. (2019)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Wei Han Hui Chen and Soujanya Poria. 2021. Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis. arXiv preprint arXiv:2109.00412(2021).  Wei Han Hui Chen and Soujanya Poria. 2021. Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis. arXiv preprint arXiv:2109.00412(2021).","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"e_1_3_2_1_11_1","volume-title":"MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis. CoRR abs\/2005.03545(2020). arxiv:2005.03545https:\/\/arxiv.org\/abs\/2005.03545","author":"Hazarika Devamanyu","year":"2020","unstructured":"Devamanyu Hazarika , Roger Zimmermann , and Soujanya Poria . 2020 . MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis. CoRR abs\/2005.03545(2020). arxiv:2005.03545https:\/\/arxiv.org\/abs\/2005.03545 Devamanyu Hazarika, Roger Zimmermann, and Soujanya Poria. 2020. MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis. CoRR abs\/2005.03545(2020). arxiv:2005.03545https:\/\/arxiv.org\/abs\/2005.03545"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63031-7_26"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-016-0406-z"},{"key":"e_1_3_2_1_15_1","volume-title":"Multibench: Multiscale benchmarks for multimodal representation learning. arXiv preprint arXiv:2107.07502(2021).","author":"Liang Paul\u00a0Pu","year":"2021","unstructured":"Paul\u00a0Pu Liang , Yiwei Lyu , Xiang Fan , Zetian Wu , Yun Cheng , Jason Wu , Leslie Chen , Peter Wu , Michelle\u00a0 A Lee , Yuke Zhu , 2021 . Multibench: Multiscale benchmarks for multimodal representation learning. arXiv preprint arXiv:2107.07502(2021). Paul\u00a0Pu Liang, Yiwei Lyu, Xiang Fan, Zetian Wu, Yun Cheng, Jason Wu, Leslie Chen, Peter Wu, Michelle\u00a0A Lee, Yuke Zhu, 2021. Multibench: Multiscale benchmarks for multimodal representation learning. arXiv preprint arXiv:2107.07502(2021)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3412841.3441958"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Zhun Liu Ying Shen Varun\u00a0Bharadhwaj Lakshminarasimhan Paul\u00a0Pu Liang Amir Zadeh and Louis-Philippe Morency. 2018. Efficient low-rank multimodal fusion with modality-specific factors. arXiv preprint arXiv:1806.00064(2018).  Zhun Liu Ying Shen Varun\u00a0Bharadhwaj Lakshminarasimhan Paul\u00a0Pu Liang Amir Zadeh and Louis-Philippe Morency. 2018. Efficient low-rank multimodal fusion with modality-specific factors. arXiv preprint arXiv:1806.00064(2018).","DOI":"10.18653\/v1\/P18-1209"},{"key":"e_1_3_2_1_18_1","unstructured":"Huaishao Luo Lei Ji Yanyong Huang Bin Wang Shenggong Ji and Tianrui Li. 2021. ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors. arXiv preprint arXiv:2112.01368(2021).  Huaishao Luo Lei Ji Yanyong Huang Bin Wang Shenggong Ji and Tianrui Li. 2021. ScaleVLAD: Improving Multimodal Sentiment Analysis via Multi-Scale Fusion of Locally Descriptors. arXiv preprint arXiv:2112.01368(2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.011"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.20"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2070481.2070509"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Xiaokang Peng Yake Wei Andong Deng Dong Wang and Di Hu. 2022. Balanced Multimodal Learning via On-the-fly Gradient Modulation. arXiv preprint arXiv:2203.15332(2022).  Xiaokang Peng Yake Wei Andong Deng Dong Wang and Di Hu. 2022. Balanced Multimodal Learning via On-the-fly Gradient Modulation. arXiv preprint arXiv:2203.15332(2022).","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"e_1_3_2_1_23_1","volume-title":"Beneath the tip of the iceberg: Current challenges and new directions in sentiment analysis research","author":"Poria Soujanya","year":"2020","unstructured":"Soujanya Poria , Devamanyu Hazarika , Navonil Majumder , and Rada Mihalcea . 2020. Beneath the tip of the iceberg: Current challenges and new directions in sentiment analysis research . IEEE Transactions on Affective Computing( 2020 ). Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, and Rada Mihalcea. 2020. Beneath the tip of the iceberg: Current challenges and new directions in sentiment analysis research. IEEE Transactions on Affective Computing(2020)."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.","author":"Poria S.","unstructured":"S. Poria , D. Hazarika , N. Majumder , G. Naik , and R. Mihalcea . 2019. MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations . In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. S. Poria, D. Hazarika, N. Majumder, G. Naik, and R. Mihalcea. 2019. MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2018.2882362"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/11573548_125"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"e_1_3_2_1_30_1","unstructured":"Afms Uddin M.\u00a0S. Monira W. Shin T.\u00a0C. Chung and S.\u00a0H. Bae. 2020. SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization. (2020).  Afms Uddin M.\u00a0S. Monira W. Shin T.\u00a0C. Chung and S.\u00a0H. Bae. 2020. SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization. (2020)."},{"key":"e_1_3_2_1_31_1","volume-title":"Visualizing data using t-SNE.Journal of machine learning research 9, 11","author":"Maaten Laurens Van\u00a0der","year":"2008","unstructured":"Laurens Van\u00a0der Maaten and Geoffrey Hinton . 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 ( 2008 ). Laurens Van\u00a0der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE.Journal of machine learning research 9, 11 (2008)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Vikas Verma Kenji Kawaguchi Alex Lamb Juho Kannala Yoshua Bengio and David Lopez-Paz. 2019. Interpolation consistency training for semi-supervised learning. arXiv preprint arXiv:1903.03825(2019).  Vikas Verma Kenji Kawaguchi Alex Lamb Juho Kannala Yoshua Bengio and David Lopez-Paz. 2019. Interpolation consistency training for semi-supervised learning. arXiv preprint arXiv:1903.03825(2019).","DOI":"10.24963\/ijcai.2019\/504"},{"key":"e_1_3_2_1_33_1","volume-title":"Manifold Mixup: Better Representations by Interpolating Hidden States.","author":"Verma V.","year":"2018","unstructured":"V. Verma , A. Lamb , C. Beckham , A. Najafi , I. Mitliagkas , A. Courville , D. Lopez-Paz , and Y. Bengio . 2018 . Manifold Mixup: Better Representations by Interpolating Hidden States. (2018). V. Verma, A. Lamb, C. Beckham, A. Najafi, I. Mitliagkas, A. Courville, D. Lopez-Paz, and Y. Bengio. 2018. Manifold Mixup: Better Representations by Interpolating Hidden States. (2018)."},{"key":"e_1_3_2_1_34_1","unstructured":"B Vva C Kk A Al B Jk B As A Yb and D Lp. 2021. Interpolation consistency training for semi-supervised learning. (2021).  B Vva C Kk A Al B Jk B As A Yb and D Lp. 2021. Interpolation consistency training for semi-supervised learning. (2021)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-3302"},{"key":"e_1_3_2_1_37_1","unstructured":"Yang Wu Yanyan Zhao Hao Yang Song Chen Bing Qin Xiaohuan Cao and Wenting Zhao. 2022. Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors. arXiv preprint arXiv:2203.00257(2022).  Yang Wu Yanyan Zhao Hao Yang Song Chen Bing Qin Xiaohuan Cao and Wenting Zhao. 2022. Sentiment Word Aware Multimodal Refinement for Multimodal Sentiment Analysis with ASR Errors. arXiv preprint arXiv:2203.00257(2022)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"S. Yoon G. Kim and K. Park. 2021. SSMix: Saliency-Based Span Mixup for Text Classification. (2021).  S. Yoon G. Kim and K. Park. 2021. SSMix: Saliency-Based Span Mixup for Text Classification. (2021).","DOI":"10.18653\/v1\/2021.findings-acl.285"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"e_1_3_2_1_40_1","unstructured":"Wenmeng Yu Hua Xu Ziqi Yuan and Jiele Wu. 2021. Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis. arXiv preprint arXiv:2102.04830(2021).  Wenmeng Yu Hua Xu Ziqi Yuan and Jiele Wu. 2021. Learning Modality-Specific Representations with Self-Supervised Multi-Task Learning for Multimodal Sentiment Analysis. arXiv preprint arXiv:2102.04830(2021)."},{"key":"e_1_3_2_1_41_1","volume-title":"International Conference on Computer Vision.","author":"Yun S.","unstructured":"S. Yun , D. Han , S. Chun , S.\u00a0 J. Oh , Y. Yoo , and J. Choe . [n.d.]. CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features . In International Conference on Computer Vision. S. Yun, D. Han, S. Chun, S.\u00a0J. Oh, Y. Yoo, and J. Choe. [n.d.]. CutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features. In International Conference on Computer Vision."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.141"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Amir Zadeh Minghai Chen Soujanya Poria Erik Cambria and Louis-Philippe Morency. 2017. Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250(2017).  Amir Zadeh Minghai Chen Soujanya Poria Erik Cambria and Louis-Philippe Morency. 2017. Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250(2017).","DOI":"10.18653\/v1\/D17-1115"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Amir Zadeh Paul\u00a0Pu Liang Navonil Mazumder Soujanya Poria Erik Cambria and Louis-Philippe Morency. 2018. Memory fusion network for multi-view sequential learning. arXiv preprint arXiv:1802.00927(2018).  Amir Zadeh Paul\u00a0Pu Liang Navonil Mazumder Soujanya Poria Erik Cambria and Louis-Philippe Morency. 2018. Memory fusion network for multi-view sequential learning. arXiv preprint arXiv:1802.00927(2018).","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"H. Zhang M. Cisse Yann\u00a0N Dauphin and D. Lopez-Paz. 2017. mixup: Beyond Empirical Risk Minimization. (2017).  H. Zhang M. Cisse Yann\u00a0N Dauphin and D. Lopez-Paz. 2017. mixup: Beyond Empirical Risk Minimization. (2017).","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"}],"event":{"name":"ICMI '22: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Bengaluru India","acronym":"ICMI '22","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2022 International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3536221.3556630","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3536221.3556630","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:48:53Z","timestamp":1750182533000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3536221.3556630"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,7]]},"references-count":48,"alternative-id":["10.1145\/3536221.3556630","10.1145\/3536221"],"URL":"https:\/\/doi.org\/10.1145\/3536221.3556630","relation":{},"subject":[],"published":{"date-parts":[[2022,11,7]]},"assertion":[{"value":"2022-11-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}