{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T01:54:38Z","timestamp":1771034078761,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"The National Key Research and Development Program of China","award":["2020YFC0811004"],"award-info":[{"award-number":["2020YFC0811004"]}]},{"name":"The Open Project of the Key Laboratory of Collection Resources Revitalizing Technology, Ministry of Culture and Tourism","award":["CRRT2022K03"],"award-info":[{"award-number":["CRRT2022K03"]}]},{"name":"The China National Foundation for Natural Sciences","award":["62072150"],"award-info":[{"award-number":["62072150"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1145\/3703619.3706033","type":"proceedings-article","created":{"date-parts":[[2025,1,19]],"date-time":"2025-01-19T18:20:52Z","timestamp":1737310852000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["FP-KDNet: Facial Perception and Knowledge Distillation Network for Emotion Recogniton in Coversation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6414-0182","authenticated-orcid":false,"given":"Chuangxin","family":"Cai","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3417-6915","authenticated-orcid":false,"given":"Xianxuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Nanjing University of Information Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4343-5949","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0900-1763","authenticated-orcid":false,"given":"Aditi","family":"Bhattarai","sequence":"additional","affiliation":[{"name":"Nanjing University of Information Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9340-7759","authenticated-orcid":false,"given":"Chunting","family":"Cai","sequence":"additional","affiliation":[{"name":"Education International Cooperation Group Shanghai Office, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0634-276X","authenticated-orcid":false,"given":"Xianliang","family":"Xia","sequence":"additional","affiliation":[{"name":"AI, Nanjing University of Information Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6264-7146","authenticated-orcid":false,"given":"Zhigeng","family":"Pan","sequence":"additional","affiliation":[{"name":"Nanjing University of Information Science and Technology, Nanjing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,1,19]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.38094\/jastt20291"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3356357"},{"key":"e_1_3_2_1_3_1","first-page":"334","article-title":"Effective ensembling classification strategy for voice and emotion recognition","volume":"15","author":"Alharbi Yasser","year":"2024","unstructured":"Yasser Alharbi. 2024. Effective ensembling classification strategy for voice and emotion recognition. International Journal of System Assurance Engineering and Management 15, 1 (2024), 334\u2013345.","journal-title":"International Journal of System Assurance Engineering and Management"},{"key":"e_1_3_2_1_4_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems 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. Advances in neural information processing systems 33 (2020), 12449\u201312460."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3650040"},{"key":"e_1_3_2_1_6_1","volume-title":"Emotional expressions reconsidered: Challenges to inferring emotion from human facial movements. Psychological science in the public interest 20, 1","author":"Barrett Lisa\u00a0Feldman","year":"2019","unstructured":"Lisa\u00a0Feldman Barrett, Ralph Adolphs, Stacy Marsella, Aleix\u00a0M Martinez, and Seth\u00a0D Pollak. 2019. Emotional expressions reconsidered: Challenges to inferring emotion from human facial movements. Psychological science in the public interest 20, 1 (2019), 1\u201368."},{"key":"e_1_3_2_1_7_1","volume-title":"Blazeface: Sub-millisecond neural face detection on mobile gpus. arXiv preprint arXiv:1907.05047","author":"Bazarevsky Valentin","year":"2019","unstructured":"Valentin Bazarevsky, Yury Kartynnik, Andrey Vakunov, Karthik Raveendran, and Matthias Grundmann. 2019. Blazeface: Sub-millisecond neural face detection on mobile gpus. arXiv preprint arXiv:1907.05047 (2019)."},{"key":"e_1_3_2_1_8_1","unstructured":"Gedas Bertasius Heng Wang and Lorenzo Torresani. 2021. Is space-time attention all you need for video understanding?. In ICML Vol.\u00a02. 4."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107708"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06012-8"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101847"},{"key":"e_1_3_2_1_15_1","volume-title":"Multi-level contrastive learning: Hierarchical alleviation of heterogeneity in multimodal sentiment analysis","author":"Fan Cunhang","year":"2024","unstructured":"Cunhang Fan, Kang Zhu, Jianhua Tao, Guofeng Yi, Jun Xue, and Zhao Lv. 2024. Multi-level contrastive learning: Hierarchical alleviation of heterogeneity in multimodal sentiment analysis. IEEE Transactions on Affective Computing (2024)."},{"key":"e_1_3_2_1_16_1","volume-title":"Facial discrimination and emotional recognition in schizophrenia and affective disorders. Archives of general psychiatry 43, 3","author":"Feinberg E","year":"1986","unstructured":"Todd\u00a0E Feinberg, Arthur Rifkin, Carrie Schaffer, and Elaine Walker. 1986. Facial discrimination and emotional recognition in schizophrenia and affective disorders. Archives of general psychiatry 43, 3 (1986), 276\u2013279."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581982"},{"key":"e_1_3_2_1_18_1","volume-title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings. In EMNLP 2021-2021 Conference on Empirical Methods in Natural Language Processing, Proceedings.","author":"Gao T","year":"2021","unstructured":"T Gao, X Yao, and Danqi Chen. 2021. SimCSE: Simple Contrastive Learning of Sentence Embeddings. In EMNLP 2021-2021 Conference on Empirical Methods in Natural Language Processing, Proceedings."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102218"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03567-4"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1142\/S0218213008004059"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108339"},{"key":"e_1_3_2_1_24_1","volume-title":"Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton. 2015. Distilling the Knowledge in a Neural Network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122946"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102019"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123723"},{"key":"e_1_3_2_1_28_1","volume-title":"Materials & Continua 75, 1","author":"Kumar Sandeep","year":"2023","unstructured":"Sandeep Kumar, Mohd\u00a0Anul Haq, Arpit Jain, C\u00a0Andy Jason, Nageswara\u00a0Rao Moparthi, Nitin Mittal, and Zamil\u00a0S Alzamil. 2023. Multilayer Neural Network Based Speech Emotion Recognition for Smart Assistance.Computers, Materials & Continua 75, 1 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"Toward emotion recognition from physiological signals in the wild: approaching the methodological issues in real-life data collection. Frontiers in psychology 11","author":"Larradet Fanny","year":"2020","unstructured":"Fanny Larradet, Radoslaw Niewiadomski, Giacinto Barresi, Darwin\u00a0G Caldwell, and Leonardo\u00a0S Mattos. 2020. Toward emotion recognition from physiological signals in the wild: approaching the methodological issues in real-life data collection. Frontiers in psychology 11 (2020), 1111."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3234777"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2023.100545"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3261279"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.126"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.076"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612277"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3257193"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-021-03407-2"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jretconser.2024.103871"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3422823"},{"key":"e_1_3_2_1_42_1","volume-title":"Text-based fine-grained emotion prediction","author":"Singh Gargi","year":"2023","unstructured":"Gargi Singh, Dhanajit Brahma, Piyush Rai, and Ashutosh Modi. 2023. Text-based fine-grained emotion prediction. IEEE Transactions on Affective Computing (2023)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBCAS.2021.3090786"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3385180"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-021-03529-7"},{"key":"e_1_3_2_1_46_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Dong Zhang Liangqing Wu Changlong Sun Shoushan Li Qiaoming Zhu and Guodong Zhou. 2019. Modeling both Context-and Speaker-Sensitive Dependence for Emotion Detection in Multi-speaker Conversations.. In IJCAI. Macao 5415\u20135421.","DOI":"10.24963\/ijcai.2019\/752"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120948"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121692"}],"event":{"name":"VRCAI '24: The 19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","location":"Nanjing Guangdong Province China","acronym":"VRCAI '24","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 19th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703619.3706033","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3703619.3706033","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T02:08:43Z","timestamp":1755914923000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3703619.3706033"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":49,"alternative-id":["10.1145\/3703619.3706033","10.1145\/3703619"],"URL":"https:\/\/doi.org\/10.1145\/3703619.3706033","relation":{},"subject":[],"published":{"date-parts":[[2024,12]]},"assertion":[{"value":"2025-01-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}