{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:21:35Z","timestamp":1776882095497,"version":"3.51.2"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447667","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"11051-11055","source":"Crossref","is-referenced-by-count":24,"title":["Fine-Grained Disentangled Representation Learning For Multimodal Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Haoqin","family":"Sun","sequence":"first","affiliation":[{"name":"Nankai University,Tianjin,China"}]},{"given":"Shiwan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nankai University,Tianjin,China"}]},{"given":"Xuechen","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University,Tianjin,China"}]},{"given":"Wenjia","family":"Zeng","sequence":"additional","affiliation":[{"name":"Lingxi (Beijing) Technology Co., Ltd."}]},{"given":"Yong","family":"Chen","sequence":"additional","affiliation":[{"name":"Lingxi (Beijing) Technology Co., Ltd."}]},{"given":"Yong","family":"Qin","sequence":"additional","affiliation":[{"name":"Nankai University,Tianjin,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2004.838534"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-4-431-67919-6_12"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326051"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20895"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2022.02.006"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-497"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref12","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00088"},{"issue":"1","key":"ref15","first-page":"2096","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"The journal of machine learning research"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747870"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747859"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10230"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095855"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2023.01.008"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095798"},{"issue":"11","key":"ref24","article-title":"Visualizing data using t-sne","volume":"9","author":"der Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447667.pdf?arnumber=10447667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:56:08Z","timestamp":1722578168000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447667","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}