{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:06:13Z","timestamp":1775815573237,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543507.3583406","type":"proceedings-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T23:30:25Z","timestamp":1682551825000},"page":"1714-1722","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["TMMDA: A New Token Mixup Multimodal Data Augmentation for Multimodal Sentiment Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5482-3895","authenticated-orcid":false,"given":"Xianbing","family":"Zhao","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6373-7531","authenticated-orcid":false,"given":"Yixin","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6608-7442","authenticated-orcid":false,"given":"Sicen","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5366-6055","authenticated-orcid":false,"given":"Xuan","family":"Zang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1395-6805","authenticated-orcid":false,"given":"Yang","family":"Xiang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0271-8246","authenticated-orcid":false,"given":"Buzhou","family":"Tang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), China"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00574"},{"key":"e_1_3_2_1_2_1","volume-title":"A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval. arXiv preprint arXiv:2208.02080","author":"Falcon Alex","year":"2022","unstructured":"Alex Falcon, Giuseppe Serra, and Oswald Lanz. 2022. A Feature-space Multimodal Data Augmentation Technique for Text-video Retrieval. arXiv preprint arXiv:2208.02080 (2022)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.390"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.486"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.528"},{"key":"e_1_3_2_1_7_1","volume-title":"ICMI 2021-Proceedings of the 2021 International Conference on Multimodal Interaction","author":"Han Wei","unstructured":"Wei Han, Hui Chen, Alexander Gelbukh, Amir Zadeh, Louis\u00a0Philippe Morency, and Soujanya Poria. 2021. Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis. In ICMI 2021-Proceedings of the 2021 International Conference on Multimodal Interaction. Association for Computing Machinery, Inc, 6\u201315."},{"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":"MixGen: A New Multi-Modal Data Augmentation. arXiv preprint arXiv:2206.08358","author":"Hao Xiaoshuai","year":"2022","unstructured":"Xiaoshuai Hao, Yi Zhu, Srikar Appalaraju, Aston Zhang, Wanqian Zhang, Bo Li, and Mu Li. 2022. MixGen: A New Multi-Modal Data Augmentation. arXiv preprint arXiv:2206.08358 (2022)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of NAACL-HLT. 4171\u20134186","author":"Ming-Wei\u00a0Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei\u00a0Chang Kenton and Lee\u00a0Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT. 4171\u20134186."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.274"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.844"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.29"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3194332"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00343"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414483"},{"key":"e_1_3_2_1_20_1","first-page":"23102","article-title":"Coco-lm: Correcting and contrasting text sequences for language model pretraining","volume":"34","author":"Meng Yu","year":"2021","unstructured":"Yu Meng, Chenyan Xiong, Payal Bajaj, Paul Bennett, Jiawei Han, Xia Song, 2021. Coco-lm: Correcting and contrasting text sequences for language model pretraining. Advances in Neural Information Processing Systems 34 (2021), 23102\u201323114.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_21_1","volume-title":"International conference on machine learning. PMLR, 2642\u20132651","author":"Odena Augustus","year":"2017","unstructured":"Augustus Odena, Christopher Olah, and Jonathon Shlens. 2017. Conditional image synthesis with auxiliary classifier gans. In International conference on machine learning. PMLR, 2642\u20132651."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"e_1_3_2_1_24_1","volume-title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification. Advances in neural information processing systems 34","author":"Rao Yongming","year":"2021","unstructured":"Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, and Cho-Jui Hsieh. 2021. Dynamicvit: Efficient vision transformers with dynamic token sparsification. Advances in neural information processing systems 34 (2021), 13937\u201313949."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"e_1_3_2_1_26_1","unstructured":"Zhiqiang Tang Yunhe Gao Yi Zhu Zhi Zhang Mu Li and Dimitris\u00a0N Metaxas. 2020. Selfnorm and crossnorm for out-of-distribution robustness. (2020)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"e_1_3_2_1_28_1","volume-title":"Learning Factorized Multimodal Representations. In International Conference on Representation Learning.","author":"Tsai Hung\u00a0Hubert","year":"2019","unstructured":"Yao-Hung\u00a0Hubert Tsai, Paul\u00a0Pu Liang, Amir Zadeh, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019. Learning Factorized Multimodal Representations. In International Conference on Representation Learning."},{"key":"e_1_3_2_1_29_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)."},{"key":"e_1_3_2_1_30_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems. 5998\u20136008."},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Machine Learning. PMLR, 6438\u20136447","author":"Verma Vikas","year":"2019","unstructured":"Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, David Lopez-Paz, and Yoshua Bengio. 2019. Manifold mixup: Better representations by interpolating hidden states. In International Conference on Machine Learning. PMLR, 6438\u20136447."},{"key":"e_1_3_2_1_32_1","volume-title":"Generating videos with scene dynamics. Advances in neural information processing systems 29","author":"Vondrick Carl","year":"2016","unstructured":"Carl Vondrick, Hamed Pirsiavash, and Antonio Torralba. 2016. Generating videos with scene dynamics. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01203"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01187"},{"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","volume-title":"EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks. arXiv e-prints","author":"Wei Jason","year":"2019","unstructured":"Jason Wei and Kai Zou. 2019. EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks. arXiv e-prints (2019), arXiv\u20131901."},{"key":"e_1_3_2_1_37_1","first-page":"6256","article-title":"Unsupervised data augmentation for consistency training","volume":"33","author":"Xie Qizhe","year":"2020","unstructured":"Qizhe Xie, Zihang Dai, Eduard Hovy, Thang Luong, and Quoc Le. 2020. Unsupervised data augmentation for consistency training. Advances in Neural Information Processing Systems 33 (2020), 6256\u20136268.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.79"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.326"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"e_1_3_2_1_43_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_1_44_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.109"},{"key":"e_1_3_2_1_46_1","volume-title":"International Conference on Learning Representations.","author":"Zhang Hongyi","year":"2018","unstructured":"Hongyi Zhang, Moustapha Cisse, Yann\u00a0N Dauphin, and David Lopez-Paz. 2018. mixup: Beyond Empirical Risk Minimization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.188"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746536"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583406","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543507.3583406","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:52Z","timestamp":1750178872000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543507.3583406"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":49,"alternative-id":["10.1145\/3543507.3583406","10.1145\/3543507"],"URL":"https:\/\/doi.org\/10.1145\/3543507.3583406","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}