{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T07:52:19Z","timestamp":1768809139536,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NSFC","award":["U2003207"],"award-info":[{"award-number":["U2003207"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612867","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"9571-9575","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Multimodal Emotion Recognition in Noisy Environment Based on Progressive Label Revision"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1494-4873","authenticated-orcid":false,"given":"Sunan","family":"Li","sequence":"first","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1355-9503","authenticated-orcid":false,"given":"Hailun","family":"lian","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1477-1020","authenticated-orcid":false,"given":"Cheng","family":"Lu","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4577-7078","authenticated-orcid":false,"given":"Yan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3653-136X","authenticated-orcid":false,"given":"Chuangao","family":"Tang","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0839-8792","authenticated-orcid":false,"given":"Yuan","family":"Zong","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7764-5179","authenticated-orcid":false,"given":"Wenming","family":"Zheng","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Brandon Amos Bartosz Ludwiczuk and Mahadev Satyanarayanan. 2016. OpenFace: A general-purpose face recognition library with mobile applications. Technical Report. Carnegie Mellon University-CS-16-118 Carnegie Mellon University School of Computer Science."},{"key":"e_1_3_2_1_2_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems","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. Advances in neural information processing systems, Vol. 33 (2020), 12449--12460."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/0005-7916(94)90063-9"},{"key":"e_1_3_2_1_4_1","volume-title":"Revisiting pre-trained models for Chinese natural language processing. arXiv preprint arXiv:2004.13922","author":"Cui Yiming","year":"2020","unstructured":"Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, and Guoping Hu. 2020. Revisiting pre-trained models for Chinese natural language processing. arXiv preprint arXiv:2004.13922 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Alexandre Defossez Gabriel Synnaeve and Yossi Adi. 2020. Real Time Speech Enhancement in the Waveform Domain. In Interspeech.","DOI":"10.21437\/Interspeech.2020-2409"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3120412"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"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":"10.1007\/s12193-015-0202-7"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830588"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of naacL-HLT","volume":"1","author":"Ming-Wei Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol. 1. 2."},{"key":"e_1_3_2_1_13_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_14_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, Vol. 25 (2012)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACIIAsia.2018.8470342"},{"key":"e_1_3_2_1_16_1","volume-title":"MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning. arXiv preprint arXiv:2304","author":"Lian Zheng","year":"2023","unstructured":"Zheng Lian, Haiyang Sun, Licai Sun, Jinming Zhao, Ye Liu, Bin Liu, Jiangyan Yi, Meng Wang, Erik Cambria, Guoying Zhao, et al. 2023. MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning. arXiv preprint arXiv:2304.08981 (2023)."},{"key":"e_1_3_2_1_17_1","volume-title":"Learning Local to Global Feature Aggregation for Speech Emotion Recognition. arXiv preprint arXiv:2306.01491","author":"Lu Cheng","year":"2023","unstructured":"Cheng Lu, Hailun Lian, Wenming Zheng, Yuan Zong, Yan Zhao, and Sunan Li. 2023. Learning Local to Global Feature Aggregation for Speech Emotion Recognition. arXiv preprint arXiv:2306.01491 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3219825"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3178232"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3077144"},{"key":"e_1_3_2_1_21_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_22_1","volume-title":"Musan: A music, speech, and noise corpus. arXiv preprint arXiv:1510.08484","author":"Snyder David","year":"2015","unstructured":"David Snyder, Guoguo Chen, and Daniel Povey. 2015. Musan: A music, speech, and noise corpus. arXiv preprint arXiv:1510.08484 (2015)."},{"key":"e_1_3_2_1_23_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, Vol. 15, 1 (2014), 1929--1958."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_1_25_1","volume-title":"Joint Face Image Restoration and Frontalization for Recognition. T-CSVT","author":"Tu Xiaoguang","year":"2021","unstructured":"Xiaoguang Tu, Jian Zhao, Qiankun Liu, Wenjie Ai, Guodong Guo, Zhifeng Li, Wei Liu, and Jiashi Feng. 2021. Joint Face Image Restoration and Frontalization for Recognition. T-CSVT (2021)."},{"key":"e_1_3_2_1_26_1","volume-title":"A class of algorithms for pattern recognition learning. Avtomat. i Telemekh","author":"Vapnik Vladimir","year":"1964","unstructured":"Vladimir Vapnik and A Ya Chervonenkis. 1964. A class of algorithms for pattern recognition learning. Avtomat. i Telemekh, Vol. 25, 6 (1964), 937--945."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00693"},{"key":"e_1_3_2_1_28_1","volume-title":"A High-Performance Face Recognition Library. arXiv preprint arXiv:2107.08621","author":"Wang Qingzhong","year":"2021","unstructured":"Qingzhong Wang, Pengfei Zhang, Haoyi Xiong, and Jian Zhao. 2021. Face.evoLVe: A High-Performance Face Recognition Library. arXiv preprint arXiv:2107.08621 (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"3D-Guided Frontal Face Generation for Pose-Invariant Recognition. T-IST","author":"Wu Hao","year":"2022","unstructured":"Hao Wu, Jianyang Gu, Xiaojin Fan, He Li, Lidong Xie, and Jian Zhao. 2022. 3D-Guided Frontal Face Generation for Pose-Invariant Recognition. T-IST (2022)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830582"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1423-y"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830585"},{"key":"e_1_3_2_1_33_1","volume-title":"Towards age-invariant face recognition. T-PAMI","author":"Zhao Jian","year":"2020","unstructured":"Jian Zhao, Shuicheng Yan, and Jiashi Feng. 2020. Towards age-invariant face recognition. T-PAMI (2020)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-679"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095388"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612867","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612867","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:14:46Z","timestamp":1755821686000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612867"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":35,"alternative-id":["10.1145\/3581783.3612867","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612867","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}