{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T19:42:20Z","timestamp":1770147740241,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62076073"],"award-info":[{"award-number":["No. 62076073"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["No. 2024A1515010237"],"award-info":[{"award-number":["No. 2024A1515010237"]}]},{"name":"RGC of the HKSAR, China","award":["UGC\/FDS16\/E17\/21"],"award-info":[{"award-number":["UGC\/FDS16\/E17\/21"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658004","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"731-739","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Modality-specific and -shared Contrastive Learning for Sentiment Analysis"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9492-2104","authenticated-orcid":false,"given":"Dahuang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0093-1128","authenticated-orcid":false,"given":"Jiuxiang","family":"You","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-5347-4274","authenticated-orcid":false,"given":"Guobo","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Guangdong University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9619-6041","authenticated-orcid":false,"given":"Lap-Kei","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Science and Technology, Hong Kong Metropolitan University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3976-0053","authenticated-orcid":false,"given":"Fu Lee","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science and Technology, Hong Kong Metropolitan University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3279-0732","authenticated-orcid":false,"given":"Zhenguo","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Science and Technology, Guangdong University of Technology, Guangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 2020 Conference on Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Caron Mathilde","year":"2020","unstructured":"Mathilde Caron, Ishan Misra, Julien Mairal, Priya Goyal, Piotr Bojanowski, and Armand Joulin. 2020. Unsupervised Learning of Visual Features by Contrasting Cluster Assignments. In Proceedings of the 2020 Conference on Neural Information Processing Systems (NeurIPS), Vol. 33. 9912--9924."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the 37th International Conference on Machine Learning (ICML)","volume":"119","author":"Chen Ting","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey E. Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the 37th International Conference on Machine Learning (ICML), Vol. 119. 1597--1607."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 15750--15758","author":"Chen Xinlei","year":"2020","unstructured":"Xinlei Chen and Kaiming He. 2020. Exploring Simple Siamese Representation Learning. In Proceedings of the 2020 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 15750--15758."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). 4171--4186","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). 4171--4186."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.025"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122454"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 2020 Conference on Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Grill Jean-Bastien","year":"2020","unstructured":"Jean-Bastien Grill, Florian Strub, Florent Altch' e, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo ' Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, R' emi Munos, and Michal Valko. 2020. Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning. In Proceedings of the 2020 Conference on Neural Information Processing Systems (NeurIPS), Vol. 33. 21271--21284."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.01.019"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103539"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 2020 Conference on Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Khosla Prannay","year":"2020","unstructured":"Prannay Khosla, Piotr Teterwak, Chen Wang, Aaron Sarna, Yonglong Tian, Phillip Isola, Aaron Maschinot, Ce Liu, and Dilip Krishnan. 2020. Supervised Contrastive Learning. In Proceedings of the 2020 Conference on Neural Information Processing Systems (NeurIPS), Vol. 33. 18661--18673."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103229"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00237"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1046"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3000510"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3172360"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414286"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 58th Conference of the Association for Computational Linguistics (ACL). 2359--2369","author":"Rahman Wasifur","unstructured":"Wasifur Rahman, Md. Kamrul Hasan, Sangwu Lee, AmirAli Bagher Zadeh, Chengfeng Mao, Louis-Philippe Morency, and Mohammed E. Hoque. 2020. Integrating Multimodal Information in Large Pretrained Transformers. In Proceedings of the 58th Conference of the Association for Computational Linguistics (ACL). 2359--2369."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"e_1_3_2_1_22_1","volume-title":"Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL). 6558--6569","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Shaojie Bai, Paul Pu Liang, J. Zico Kolter, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019a. Multimodal Transformer for Unaligned Multimodal Language Sequences. In Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL). 6558--6569."},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 7th International Conference on Learning Representations (ICLR).","author":"Hubert Tsai Yao-Hung","year":"2019","unstructured":"Yao-Hung Hubert Tsai, Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2019b. Learning Factorized Multimodal Representations. In Proceedings of the 7th International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 2017 IEEE International Conference on Multimedia and Expo (ICME). 949--954","author":"Wang Haohan","unstructured":"Haohan Wang, Aaksha Meghawat, Louis-Philippe Morency, and Eric P. Xing. 2017. Select-Additive Learning: Improving Generalization in Multimodal Sentiment Analysis. In Proceedings of the 2017 IEEE International Conference on Multimedia and Expo (ICME). 949--954."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 3rd International Conference on Computer Vision Theory and Applications (VISAPP). 145--151","author":"Wimmer Matthias","year":"2008","unstructured":"Matthias Wimmer, Bj\" orn W. Schuller, Dejan Arsic, Gerhard Rigoll, and Bernd Radig. 2008. Low-Level Fusion of Audio, Video Feature for Multi-Modal Emotion Recognition. In Proceedings of the 3rd International Conference on Computer Vision Theory and Applications (VISAPP). 145--151."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 56th Conference of the Association for Computational Linguistics (ACL). 2236--2246","author":"Zadeh Amir","year":"2018","unstructured":"Amir Zadeh, Paul Pu Liang, Soujanya Poria, Erik Cambria, and Louis-Philippe Morency. 2018b. Multimodal Language Analysis in the Wild: Carnegie Mellon University-MOSEI Dataset and Interpretable Dynamic Fusion Graph. In Proceedings of the 56th Conference of the Association for Computational Linguistics (ACL). 2236--2246."},{"key":"e_1_3_2_1_33_1","volume-title":"MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos. CoRR","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. CoRR , Vol. abs\/1606.06259 (2016)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.04.003"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102097"}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658004","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:53:29Z","timestamp":1755766409000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658004"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":35,"alternative-id":["10.1145\/3652583.3658004","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658004","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}