{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:28:18Z","timestamp":1775230098351,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,29]],"date-time":"2023-10-29T00:00:00Z","timestamp":1698537600000},"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":[[2023,10,29]]},"DOI":"10.1145\/3607865.3613182","type":"proceedings-article","created":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T18:12:36Z","timestamp":1697566356000},"page":"67-73","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Semi-supervised Multimodal Emotion Recognition with Consensus Decision-making and Label Correction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0865-9422","authenticated-orcid":false,"given":"Jingguang","family":"Tian","sequence":"first","affiliation":[{"name":"Hithink RoyalFlush AI Research Institute, HangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6348-0409","authenticated-orcid":false,"given":"Desheng","family":"Hu","sequence":"additional","affiliation":[{"name":"Hithink RoyalFlush AI Research Institute, HangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1917-4479","authenticated-orcid":false,"given":"Xiaohan","family":"Shi","sequence":"additional","affiliation":[{"name":"Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6489-5220","authenticated-orcid":false,"given":"Jiajun","family":"He","sequence":"additional","affiliation":[{"name":"Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8958-0341","authenticated-orcid":false,"given":"Xingfeng","family":"Li","sequence":"additional","affiliation":[{"name":"Hainan University, HaiKou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2147-1835","authenticated-orcid":false,"given":"Yuan","family":"Gao","sequence":"additional","affiliation":[{"name":"Kyoto University, Kyoto, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8146-1279","authenticated-orcid":false,"given":"Tomoki","family":"Toda","sequence":"additional","affiliation":[{"name":"Nagoya University, Nagoya, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2771-1398","authenticated-orcid":false,"given":"Xinkang","family":"Xu","sequence":"additional","affiliation":[{"name":"Hithink RoyalFlush AI Research Institute, HangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1433-9324","authenticated-orcid":false,"given":"Xinhui","family":"Hu","sequence":"additional","affiliation":[{"name":"Hithink RoyalFlush AI Research Institute, HangZhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,29]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952552"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3068045"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3172954"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747095"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.38094\/jastt20291"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108580"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747754"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iswa.2022.200171"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/703"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747723"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2067"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00615"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_16_1","volume-title":"Hubert: Self-supervised speech representation learning by masked prediction of hidden units","author":"Hsu Wei-Ning","year":"2021","unstructured":"Wei-Ning Hsu , Benjamin Bolte , Yao-Hung Hubert Tsai , Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. Hubert: Self-supervised speech representation learning by masked prediction of hidden units . IEEE\/ACM Transactions on Audio, Speech, and Language Processing , 29:3451--3460, 2021 . Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 29:3451--3460, 2021."},{"key":"e_1_3_2_1_17_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, 33:12449--12460","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski , Yuhao Zhou , Abdelrahman Mohamed , and Michael Auli . wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, 33:12449--12460 , 2020 . Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, 33:12449--12460, 2020."},{"key":"e_1_3_2_1_18_1","volume-title":"IEEE","author":"Hershey Shawn","year":"2017","unstructured":"Shawn Hershey , Sourish Chaudhuri , Daniel PW Ellis , Jort F Gemmeke , Aren Jansen , R Channing Moore , Manoj Plakal , Devin Platt , Rif A Saurous , Bryan Seybold , Cnn architectures for large-scale audio classification. In 2017 ieee international conference on acoustics, speech and signal processing (icassp), pages 131--135 . IEEE , 2017 . Shawn Hershey, Sourish Chaudhuri, Daniel PW Ellis, Jort F Gemmeke, Aren Jansen, R Channing Moore, Manoj Plakal, Devin Platt, Rif A Saurous, Bryan Seybold, et al. Cnn architectures for large-scale audio classification. In 2017 ieee international conference on acoustics, speech and signal processing (icassp), pages 131--135. IEEE, 2017."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682541"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023632"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2983669"},{"key":"e_1_3_2_1_22_1","article-title":"Semi-supervised multi-modal interaction network for conversational emotion recognition","author":"Lian Zheng","year":"2022","unstructured":"Zheng Lian , Bin Liu , and Jianhua Tao . Smin : Semi-supervised multi-modal interaction network for conversational emotion recognition . IEEE Transactions on Affective Computing , 2022 . Zheng Lian, Bin Liu, and Jianhua Tao. Smin: Semi-supervised multi-modal interaction network for conversational emotion recognition. IEEE Transactions on Affective Computing, 2022.","journal-title":"IEEE Transactions on Affective Computing"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746910"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05855-6"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_2_1_26_1","volume-title":"Mer 2023: Multi-label learning, modality robustness, and semi-supervised learning. arXiv preprint arXiv:2304.08981","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 , Mer 2023: Multi-label learning, modality robustness, and semi-supervised learning. arXiv preprint arXiv:2304.08981 , 2023 . Zheng Lian, Haiyang Sun, Licai Sun, Jinming Zhao, Ye Liu, Bin Liu, Jiangyan Yi, Meng Wang, Erik Cambria, Guoying Zhao, et al. Mer 2023: Multi-label learning, modality robustness, and semi-supervised learning. arXiv preprint arXiv:2304.08981, 2023."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1280"},{"key":"e_1_3_2_1_28_1","volume-title":"Wenet: Production oriented streaming and non-streaming end-to-end speech recognition toolkit. arXiv preprint arXiv:2102.01547","author":"Yao Zhuoyuan","year":"2021","unstructured":"Zhuoyuan Yao , DiWu, XiongWang, Binbin Zhang , Fan Yu , Chao Yang , Zhendong Peng , Xiaoyu Chen , Lei Xie , and Xin Lei . Wenet: Production oriented streaming and non-streaming end-to-end speech recognition toolkit. arXiv preprint arXiv:2102.01547 , 2021 . Zhuoyuan Yao, DiWu, XiongWang, Binbin Zhang, Fan Yu, Chao Yang, Zhendong Peng, Xiaoyu Chen, Lei Xie, and Xin Lei. Wenet: Production oriented streaming and non-streaming end-to-end speech recognition toolkit. arXiv preprint arXiv:2102.01547, 2021."},{"key":"e_1_3_2_1_29_1","first-page":"28492","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2023","unstructured":"Alec Radford , JongWook Kim , Tao Xu , Greg Brockman , Christine McLeavey , and Ilya Sutskever . Robust speech recognition via large-scale weak supervision . In International Conference on Machine Learning , pages 28492 -- 28518 . PMLR, 2023 . Alec Radford, JongWook Kim, Tao Xu, Greg Brockman, Christine McLeavey, and Ilya Sutskever. Robust speech recognition via large-scale weak supervision. In International Conference on Machine Learning, pages 28492--28518. PMLR, 2023."},{"key":"e_1_3_2_1_30_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 . Revisiting pre-trained models for chinese natural language processing. arXiv preprint arXiv:2004.13922 , 2020 . Yiming Cui, Wanxiang Che, Ting Liu, Bing Qin, Shijin Wang, and Guoping Hu. Revisiting pre-trained models for chinese natural language processing. arXiv preprint arXiv:2004.13922, 2020."},{"key":"e_1_3_2_1_31_1","first-page":"1","volume-title":"Openface: an open source facial behavior analysis toolkit. In 2016 IEEE winter conference on applications of computer vision (WACV)","author":"Tadas","year":"2016","unstructured":"Tadas Baltru\"aitis, Peter Robinson , and Louis-Philippe Morency . Openface: an open source facial behavior analysis toolkit. In 2016 IEEE winter conference on applications of computer vision (WACV) , pages 1 -- 10 . IEEE , 2016 . Tadas Baltru\"aitis, Peter Robinson, and Louis-Philippe Morency. Openface: an open source facial behavior analysis toolkit. In 2016 IEEE winter conference on applications of computer vision (WACV), pages 1--10. IEEE, 2016."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"e_1_3_2_1_34_1","volume-title":"3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In Yoshua Bengio and Yann LeCun, editors , 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings , 2015 . Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In Yoshua Bengio and Yann LeCun, editors, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7--9, 2015, Conference Track Proceedings, 2015."},{"key":"e_1_3_2_1_35_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1):1929--1958","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava , Geoffrey Hinton , Alex Krizhevsky , Ilya Sutskever , and Ruslan Salakhutdinov . Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1):1929--1958 , 2014 . Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1):1929--1958, 2014."}],"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 1st International Workshop on Multimodal and Responsible Affective Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3607865.3613182","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3607865.3613182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:06Z","timestamp":1750178226000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3607865.3613182"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,29]]},"references-count":35,"alternative-id":["10.1145\/3607865.3613182","10.1145\/3607865"],"URL":"https:\/\/doi.org\/10.1145\/3607865.3613182","relation":{},"subject":[],"published":{"date-parts":[[2023,10,29]]},"assertion":[{"value":"2023-10-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}