{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T09:45:28Z","timestamp":1784454328654,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Natural Science Foundation of China","award":["No. 62076133, 62006117, and 62272232"],"award-info":[{"award-number":["No. 62076133, 62006117, and 62272232"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681638","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"622-631","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["A Unimodal Valence-Arousal Driven Contrastive Learning Framework for Multimodal Multi-Label Emotion Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1515-5289","authenticated-orcid":false,"given":"Wenjie","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8380-0609","authenticated-orcid":false,"given":"Jianfei","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0621-1058","authenticated-orcid":false,"given":"Rui","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1034"},{"key":"e_1_3_2_1_2_1","volume-title":"Schuller","author":"Amiriparian Shahin","year":"2023","unstructured":"Shahin Amiriparian, Lukas Christ, Andreas K\u00f6nig, Alan S. Cowen, Eva-Maria Messner, Erik Cambria, and Bj\u00f6rn W. Schuller. 2023. MuSe 2023 Challenge: Multimodal Prediction of Mimicked Emotions, Cross-Cultural Humour, and Personalised Recognition of Affects. In Proceedings of ACM MM."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612517"},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of ICLR.","author":"Bahdanau Dzmitry","year":"2015","unstructured":"Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of ICLR."},{"key":"e_1_3_2_1_5_1","volume-title":"Solving the emotion paradox: Categorization and the experience of emotion. Personality and social psychology review","author":"Barrett Lisa Feldman","year":"2006","unstructured":"Lisa Feldman Barrett. 2006. Solving the emotion paradox: Categorization and the experience of emotion. Personality and social psychology review (2006)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-2092"},{"key":"e_1_3_2_1_7_1","volume-title":"Samuel Kim, Jeannette N. Chang, Sungbok Lee, and Shrikanth S. Narayanan.","author":"Busso Carlos","year":"2008","unstructured":"Carlos Busso, Murtaza Bulut, Chi-Chun Lee, Ebrahim (Abe) Kazemzadeh, Emily Mower Provost, Samuel Kim, Jeannette N. Chang, Sungbok Lee, and Shrikanth S. Narayanan. 2008. IEMOCAP: interactive emotional dyadic motion capture database. Language Resources and Evaluation (2008)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.195"},{"key":"e_1_3_2_1_10_1","volume-title":"Unsupervised cross-lingual representation learning for speech recognition. arXiv preprint arXiv:2006.13979","author":"Conneau Alexis","year":"2020","unstructured":"Alexis Conneau, Alexei Baevski, Ronan Collobert, Abdelrahman Mohamed, and Michael Auli. 2020. Unsupervised cross-lingual representation learning for speech recognition. arXiv preprint arXiv:2006.13979 (2020)."},{"key":"e_1_3_2_1_11_1","volume-title":"Multi-label emotion detection via emotion-specified feature extraction and emotion correlation learning","author":"Deng Jiawen","year":"2020","unstructured":"Jiawen Deng and Fuji Ren. 2020. Multi-label emotion detection via emotion-specified feature extraction and emotion correlation learning. IEEE Transactions on Affective Computing (2020)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001390"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6271"},{"key":"e_1_3_2_1_14_1","volume-title":"Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions. Information Fusion","author":"Gandhi Ankita","year":"2023","unstructured":"Ankita Gandhi, Kinjal Adhvaryu, Soujanya Poria, Erik Cambria, and Amir Hussain. 2023. Multimodal sentiment analysis: A systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions. Information Fusion (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583258"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.224"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"e_1_3_2_1_19_1","volume-title":"Deep Learning for Depression Recognition with Audiovisual Cues: A Review. ArXiv","author":"He Lang","year":"2021","unstructured":"Lang He, Mingyue Niu, Prayag Tiwari, Pekka Marttinen, Rui Su, Jiewei Jiang, Chenguang Guo, Hongyu Wang, Songtao Ding, Zhongmin Wang, Wei Dang, and Xiaoying Pan. 2021. Deep Learning for Depression Recognition with Audiovisual Cues: A Review. ArXiv (2021)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.606"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.375"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413577"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613459"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of NeurIPS.","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 NeurIPS."},{"key":"e_1_3_2_1_27_1","volume-title":"Action Unit Detection & Emotional Reaction Intensity Estimation Challenges. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops.","author":"Kollias Dimitrios D.","year":"2023","unstructured":"Dimitrios D. Kollias, Panagiotis Tzirakis, Alice Baird, Alan S. Cowen, and Stefanos Zafeiriou. 2023. ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Solomon Kullback and R. A. Leibler. 1951. On Information and Sufficiency. Annals of Mathematical Statistics (1951).","DOI":"10.1214\/aoms\/1177729694"},{"key":"e_1_3_2_1_29_1","volume-title":"Instructerc: Reforming emotion recognition in conversation with a retrieval multi-task llms framework. arXiv preprint arXiv:2309.11911","author":"Lei Shanglin","year":"2023","unstructured":"Shanglin Lei, Guanting Dong, Xiaoping Wang, Keheng Wang, and Sirui Wang. 2023. Instructerc: Reforming emotion recognition in conversation with a retrieval multi-task llms framework. arXiv preprint arXiv:2309.11911 (2023)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26541"},{"key":"e_1_3_2_1_31_1","volume-title":"GCNet: graph completion network for incomplete multimodal learning in conversation","author":"Lian Zheng","year":"2023","unstructured":"Zheng Lian, Lan Chen, Licai Sun, Bin Liu, and Jianhua Tao. 2023. GCNet: graph completion network for incomplete multimodal learning in conversation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning. In Proceedings of ACM MM.","author":"Lian Zheng","year":"2023","unstructured":"Zheng Lian, Haiyang Sun, Licai Sun, Jinming Zhao, Ye Liu, B. Liu, Jiangyan Yi, Meng Wang, E. Cambria, Guoying Zhao, Bj\u00f6rn Schuller, and Jianhua Tao. 2023. MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning. In Proceedings of ACM MM."},{"key":"e_1_3_2_1_33_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_34_1","volume-title":"EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis. arXiv preprint arXiv:2401.08508","author":"Liu Zhiwei","year":"2024","unstructured":"Zhiwei Liu, Kailai Yang, Tianlin Zhang, Qianqian Xie, Zeping Yu, and Sophia Ananiadou. 2024. EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis. arXiv preprint arXiv:2401.08508 (2024)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2736999"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.360"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.298"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5492"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1017"},{"key":"e_1_3_2_1_41_1","volume-title":"Affectnet: A database for facial expression, valence, and arousal computing in the wild","author":"Mollahosseini Ali","year":"2017","unstructured":"Ali Mollahosseini, Behzad Hasani, and Mohammad H Mahoor. 2017. Affectnet: A database for facial expression, valence, and arousal computing in the wild. IEEE Transactions on Affective Computing (2017)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612555"},{"key":"e_1_3_2_1_43_1","volume-title":"Oh","author":"Park Sungjoon","year":"2019","unstructured":"Sungjoon Park, Jiseon Kim, Seonghyeon Ye, Jaeyeol Jeon, Heeyoung Park, and Alice H. Oh. 2019. Dimensional Emotion Detection from Categorical Emotion. In Proceedings of EMNLP."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548278"},{"key":"e_1_3_2_1_46_1","volume-title":"AVEC 2012: the continuous audio\/visual emotion challenge. In Proceedings of International Conference on Multimodal Interaction.","author":"Schuller Bj\u00f6rn","year":"2012","unstructured":"Bj\u00f6rn Schuller, Michel F. Valstar, Florian Eyben, Roddy Cowie, and Maja Pantic. 2012. AVEC 2012: the continuous audio\/visual emotion challenge. In Proceedings of International Conference on Multimodal Interaction."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17625"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.123"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00248"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"e_1_3_2_1_51_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"Estimation of continuous valence and arousal levels from faces in naturalistic conditions. Nature Machine Intelligence","author":"Toisoul Antoine","year":"2021","unstructured":"Antoine Toisoul, Jean Kossaifi, Adrian Bulat, Georgios Tzimiropoulos, and Maja Pantic. 2021. Estimation of continuous valence and arousal levels from faces in naturalistic conditions. Nature Machine Intelligence (2021)."},{"key":"e_1_3_2_1_53_1","volume-title":"Proceedings of ACL.","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. 2019. Multimodal transformer for unaligned multimodal language sequences. In Proceedings of ACL."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.813"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2512530.2512533"},{"key":"e_1_3_2_1_56_1","volume-title":"Visualizing data using t-SNE. Journal of machine learning research","author":"der Maaten Laurens Van","year":"2008","unstructured":"Laurens Van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-SNE. Journal of machine learning research (2008)."},{"key":"e_1_3_2_1_57_1","volume-title":"Dawn of the transformer era in speech emotion recognition: closing the valence gap","author":"Wagner Johannes","year":"2023","unstructured":"Johannes Wagner, Andreas Triantafyllopoulos, Hagen Wierstorf, Maximilian Schmitt, Felix Burkhardt, Florian Eyben, and Bj\u00f6rn W Schuller. 2023. Dawn of the transformer era in speech emotion recognition: closing the valence gap. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.184"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3243463"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.291"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17686"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20895"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.391"},{"key":"e_1_3_2_1_67_1","volume-title":"Is ChatGPT Equipped with Emotional Dialogue Capabilities? arXiv preprint arXiv:2304.09582","author":"Zhao Weixiang","year":"2023","unstructured":"Weixiang Zhao, Yanyan Zhao, Xin Lu, Shilong Wang, Yanpeng Tong, and Bing Qin. 2023. Is ChatGPT Equipped with Emotional Dialogue Capabilities? arXiv preprint arXiv:2304.09582 (2023)."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.861"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1016"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.96"},{"key":"e_1_3_2_1_71_1","volume-title":"Prompt Consistency for Multi-label Textual Emotion Detection","author":"Zhou Yangyang","year":"2023","unstructured":"Yangyang Zhou, Xin Kang, and Fuji Ren. 2023. Prompt Consistency for Multi-label Textual Emotion Detection. IEEE Transactions on Affective Computing (2023)."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1045"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681638","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681638"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":72,"alternative-id":["10.1145\/3664647.3681638","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681638","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}