{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:14:36Z","timestamp":1775229276678,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,9]],"date-time":"2023-10-09T00:00:00Z","timestamp":1696809600000},"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":[[2023,10,9]]},"DOI":"10.1145\/3577190.3616544","type":"proceedings-article","created":{"date-parts":[[2023,10,7]],"date-time":"2023-10-07T22:30:48Z","timestamp":1696717848000},"page":"741-745","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Audio-Visual Group-based Emotion Recognition using Local and Global Feature Aggregation based Multi-Task Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1494-4873","authenticated-orcid":false,"given":"Sunan","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Southeast University, 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":"School of Information Science and Engineering, Southeast University, 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":"School of Biological Science and Medical Engineering, Southeast University, 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":"School of Information Science and Engineering, Southeast University, 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":"School of Biological Science and Medical Engineering, Southeast University, 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":"School of Biological Science and Medical Engineering, Southeast University, 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":"Key Laboratory of Child Development and Learning Science of Ministry of Education, Southeast University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,9]]},"reference":[{"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 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. 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_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417973"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3616545"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0202-7"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830588"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of naacL-HLT, Vol.\u00a01. 2.","author":"Ming-Wei\u00a0Chang Jacob Devlin","year":"2019","unstructured":"Jacob Devlin Ming-Wei\u00a0Chang Kenton and Lee\u00a0Kristina Toutanova . 2019 . Bert: Pre-training of deep bidirectional transformers for language understanding . In Proceedings of naacL-HLT, Vol.\u00a01. 2. Jacob Devlin Ming-Wei\u00a0Chang Kenton and Lee\u00a0Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of naacL-HLT, Vol.\u00a01. 2."},{"key":"e_1_3_2_1_11_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 ). 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_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3219825"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417969"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417971"},{"key":"e_1_3_2_1_15_1","volume-title":"A class of algorithms for pattern recognition learning. Avtomat. i Telemekh 25, 6","author":"Vapnik Vladimir","year":"1964","unstructured":"Vladimir Vapnik and A\u00a0Ya Chervonenkis . 1964. A class of algorithms for pattern recognition learning. Avtomat. i Telemekh 25, 6 ( 1964 ), 937\u2013945. Vladimir Vapnik and A\u00a0Ya Chervonenkis. 1964. A class of algorithms for pattern recognition learning. Avtomat. i Telemekh 25, 6 (1964), 937\u2013945."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3417960"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830582"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2830585"}],"event":{"name":"ICMI '23: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Paris France","acronym":"ICMI '23","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577190.3616544","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3577190.3616544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:02Z","timestamp":1750178222000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577190.3616544"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,9]]},"references-count":17,"alternative-id":["10.1145\/3577190.3616544","10.1145\/3577190"],"URL":"https:\/\/doi.org\/10.1145\/3577190.3616544","relation":{},"subject":[],"published":{"date-parts":[[2023,10,9]]},"assertion":[{"value":"2023-10-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}