{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:46:08Z","timestamp":1777502768809,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":25,"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":"Key Research and Development Program of Shaanxi","award":["2022ZDLGY06-03"],"award-info":[{"award-number":["2022ZDLGY06-03"]}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62236006"],"award-info":[{"award-number":["62236006"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3689092.3689407","type":"proceedings-article","created":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T18:33:17Z","timestamp":1729708397000},"page":"67-71","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Improving Multimodal Emotion Recognition by Leveraging Acoustic Adaptation and Visual Alignment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1136-8279","authenticated-orcid":false,"given":"Zhixian","family":"Zhao","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7164-5840","authenticated-orcid":false,"given":"Haifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Shaanxi University of Science and Technology, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6236-6431","authenticated-orcid":false,"given":"Xi","family":"Li","sequence":"additional","affiliation":[{"name":"Shaanxi University of Science and Technology, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-8499","authenticated-orcid":false,"given":"Dongmei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory & Northwestern Polytechnical University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8234-0823","authenticated-orcid":false,"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning. 1416--1429","author":"Baevski Alexei","year":"2023","unstructured":"Alexei Baevski, Arun Babu, Wei-Ning Hsu, and Michael Auli. 2023. Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language. In Proceedings of the 40th International Conference on Machine Learning. 1416--1429."},{"key":"e_1_3_2_1_2_1","first-page":"12449","article-title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","volume":"33","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. In Advances in Neural Information Processing Systems, Vol. 33. 12449--12460.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.10.005"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447640"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446645"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446997"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446825"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746250"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524499"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612836"},{"key":"e_1_3_2_1_14_1","volume-title":"MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition. https:\/\/arxiv.org\/abs\/2404","author":"Lian Zheng","year":"2024","unstructured":"Zheng Lian, Haiyang Sun, Licai Sun, Zhuofan Wen, Siyuan Zhang, Shun Chen, Hao Gu, Jinming Zhao, Ziyang Ma, Xie Chen, Jiangyan Yi, Rui Liu, Kele Xu, Bin Liu, Erik Cambria, Guoying Zhao, Bj\u00f6rn W. Schuller, and Jianhua Tao. 2024. MER 2024: Semi-Supervised Learning, Noise Robustness, and Open-Vocabulary Multimodal Emotion Recognition. https:\/\/arxiv.org\/abs\/2404.17113"},{"key":"e_1_3_2_1_15_1","first-page":"34892","article-title":"Visual Instruction Tuning","volume":"36","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruction Tuning. In Advances in Neural Information Processing Systems, Vol. 36. 34892--34916.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Yu Pan Yanni Hu Yuguang Yang Wen Fei Jixun Yao Heng Lu Lei Ma and Jianjun Zhao. 2024. GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition. In ICASSP 2024 - 2024 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). 10021--10025. https:\/\/doi.org\/10.1109\/ICASSP48485.2024.10448394","DOI":"10.1109\/ICASSP48485.2024.10448394"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning","volume":"139","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, Vol. 139. PMLR, 8748--8763."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning","volume":"202","author":"Radford Alec","year":"2023","unstructured":"Alec Radford, Jong Wook Kim, Tao Xu, Greg Brockman, Christine Mcleavey, and Ilya Sutskever. 2023. Robust Speech Recognition via Large-Scale Weak Supervision. In Proceedings of the 40th International Conference on Machine Learning, Vol. 202. PMLR, 28492--28518."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101429"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446040"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.3390\/make5040083"},{"key":"e_1_3_2_1_22_1","unstructured":"Yingzhi Wang Abdelmoumene Boumadane and Abdelwahab Heba. 2022. A Fine-tuned Wav2vec 2.0\/HuBERT Benchmark For Speech Emotion Recognition Speaker Verification and Spoken Language Understanding. https:\/\/arxiv.org\/abs\/2111.02735"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"Yusong Wu Ke Chen Tianyu Zhang Yuchen Hui Taylor Berg-Kirkpatrick and Shlomo Dubnov. 2023. Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP). 1--5. https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10095969","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"e_1_3_2_1_24_1","unstructured":"Aiyuan Yang Bin Xiao Bingning Wang Borong Zhang Ce Bian Chao Yin and Chenxu Lv. 2023. Baichuan 2: Open Large-scale Language Models. https:\/\/arxiv.org\/abs\/2309.10305"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"}],"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 2nd International Workshop on Multimodal and Responsible Affective Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689092.3689407","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689092.3689407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T02:00:02Z","timestamp":1755914402000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689092.3689407"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":25,"alternative-id":["10.1145\/3689092.3689407","10.1145\/3689092"],"URL":"https:\/\/doi.org\/10.1145\/3689092.3689407","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"}}]}}