{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T00:23:36Z","timestamp":1770337416516,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","funder":[{"name":"the National Natural Science Foundation of China","award":["No. 62201404"],"award-info":[{"award-number":["No. 62201404"]}]},{"name":"the Startup Foundation for Introducing Talent of NUIST","award":["No. 2024r061"],"award-info":[{"award-number":["No. 2024r061"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,13]]},"DOI":"10.1145\/3779232.3779470","type":"proceedings-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:49:12Z","timestamp":1770292152000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ALTSA: Adaptive Latent-space Teacher - Student Architecture for Emotion Recognition in Conversation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0900-1763","authenticated-orcid":false,"given":"Aditi","family":"Bhattarai","sequence":"first","affiliation":[{"name":"Nanjing university of information science and technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6414-0182","authenticated-orcid":false,"given":"Chuangxin","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing university of information science and technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2889-4670","authenticated-orcid":false,"given":"Mengxia","family":"Li","sequence":"additional","affiliation":[{"name":"Dongfeng Motor Corporation Research and Development Institute, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9111-0499","authenticated-orcid":false,"given":"Kao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing university of information science and technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1341-5585","authenticated-orcid":false,"given":"Ming","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing university of information science and technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"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"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"key":"e_1_3_3_1_2_1","doi-asserted-by":"crossref","unstructured":"Sharmeen M Saleem\u00a0Abdullah Abdullah Siddeeq Y\u00a0Ameen Ameen Mohammed\u00a0AM Sadeeq and Subhi Zeebaree. 2021. Multimodal emotion recognition using deep learning. Journal of Applied Science and Technology Trends 2 01 (2021) 73\u201379.","DOI":"10.38094\/jastt20291"},{"key":"e_1_3_3_1_3_1","first-page":"1298","volume-title":"International conference on machine learning","author":"Baevski Alexei","year":"2022","unstructured":"Alexei Baevski, Wei-Ning Hsu, Qiantong Xu, Arun Babu, Jiatao Gu, and Michael Auli. 2022. Data2vec: A general framework for self-supervised learning in speech, vision and language. In International conference on machine learning. PMLR, 1298\u20131312."},{"key":"e_1_3_3_1_4_1","doi-asserted-by":"crossref","unstructured":"Saira Bano Nicola Tonellotto Pietro Cassar\u00e0 and Alberto Gotta. 2024. FedCMD: A federated cross-modal knowledge distillation for drivers\u2019 emotion recognition. ACM Transactions on Intelligent Systems and Technology 15 3 (2024) 1\u201327.","DOI":"10.1145\/3650040"},{"key":"e_1_3_3_1_5_1","first-page":"4","volume-title":"Icml","author":"Bertasius Gedas","year":"2021","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_3_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581982"},{"key":"e_1_3_3_1_7_1","doi-asserted-by":"crossref","unstructured":"Jianping Gou Baosheng Yu Stephen\u00a0J Maybank and Dacheng Tao. 2021. Knowledge distillation: A survey. International journal of computer vision 129 6 (2021) 1789\u20131819.","DOI":"10.1007\/s11263-021-01453-z"},{"key":"e_1_3_3_1_8_1","unstructured":"Tao Huang Shan You Fei Wang Chen Qian and Chang Xu. 2022. Knowledge distillation from a stronger teacher. Advances in Neural Information Processing Systems 35 (2022) 33716\u201333727."},{"key":"e_1_3_3_1_9_1","doi-asserted-by":"crossref","unstructured":"Mustaqeem Khan Wail Gueaieb Abdulmotaleb El\u00a0Saddik and Soonil Kwon. 2024. MSER: Multimodal speech emotion recognition using cross-attention with deep fusion. Expert Systems with Applications 245 (2024) 122946.","DOI":"10.1016\/j.eswa.2023.122946"},{"key":"e_1_3_3_1_10_1","doi-asserted-by":"crossref","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).","DOI":"10.32604\/cmc.2023.028631"},{"key":"e_1_3_3_1_11_1","doi-asserted-by":"crossref","unstructured":"Sze\u00a0Chit Leong Yuk\u00a0Ming Tang Chung\u00a0Hin Lai and CKM Lee. 2023. Facial expression and body gesture emotion recognition: A systematic review on the use of visual data in affective computing. Computer science review 48 (2023) 100545.","DOI":"10.1016\/j.cosrev.2023.100545"},{"key":"e_1_3_3_1_12_1","doi-asserted-by":"crossref","unstructured":"Jiang Li Xiaoping Wang Guoqing Lv and Zhigang Zeng. 2023. GA2MIF: Graph and attention based two-stage multi-source information fusion for conversational emotion detection. IEEE Transactions on affective computing 15 1 (2023) 130\u2013143.","DOI":"10.1109\/TAFFC.2023.3261279"},{"key":"e_1_3_3_1_13_1","doi-asserted-by":"crossref","unstructured":"Wentao Ma Qingchao Chen Tongqing Zhou Shan Zhao and Zhiping Cai. 2023. Using multimodal contrastive knowledge distillation for video-text retrieval. IEEE Transactions on Circuits and Systems for Video Technology 33 10 (2023) 5486\u20135497.","DOI":"10.1109\/TCSVT.2023.3257193"},{"key":"e_1_3_3_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"e_1_3_3_1_15_1","doi-asserted-by":"crossref","unstructured":"Bei Pan Kaoru Hirota Zhiyang Jia Linhui Zhao Xiaoming Jin and Yaping Dai. 2023. Multimodal emotion recognition based on feature selection and extreme learning machine in video clips. Journal of Ambient Intelligence and Humanized Computing 14 3 (2023) 1903\u20131917.","DOI":"10.1007\/s12652-021-03407-2"},{"key":"e_1_3_3_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"e_1_3_3_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.347"},{"key":"e_1_3_3_1_18_1","doi-asserted-by":"crossref","unstructured":"Teng Sun Yinwei Wei Juntong Ni Zixin Liu Xuemeng Song Yaowei Wang and Liqiang Nie. 2024. Muti-modal emotion recognition via hierarchical knowledge distillation. IEEE Transactions on Multimedia 26 (2024) 9036\u20139046.","DOI":"10.1109\/TMM.2024.3385180"},{"key":"e_1_3_3_1_19_1","unstructured":"Taeyang Yun Hyunkuk Lim Jeonghwan Lee and Min Song. 2024. Telme: Teacher-leading multimodal fusion network for emotion recognition in conversation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.12987 (2024)."},{"key":"e_1_3_3_1_20_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/752"},{"key":"e_1_3_3_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.861"}],"event":{"name":"VRCAI '25: The 20th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry","location":"Macau China","acronym":"VRCAI '25","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 2025 20th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3779232.3779470","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T11:50:29Z","timestamp":1770292229000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779232.3779470"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,13]]},"references-count":20,"alternative-id":["10.1145\/3779232.3779470","10.1145\/3779232"],"URL":"https:\/\/doi.org\/10.1145\/3779232.3779470","relation":{},"subject":[],"published":{"date-parts":[[2025,12,13]]},"assertion":[{"value":"2026-02-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}