{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T16:19:41Z","timestamp":1776183581380,"version":"3.50.1"},"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447640","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"8030-8034","source":"Crossref","is-referenced-by-count":13,"title":["AttA-NET: Attention Aggregation Network for Audio-Visual Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Ruijia","family":"Fan","sequence":"first","affiliation":[{"name":"Peking University,Shenzhen Graduate School,National Key Laboratory of General Artificial Intelligence,China"}]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"Peking University,Shenzhen Graduate School,National Key Laboratory of General Artificial Intelligence,China"}]},{"given":"Yidi","family":"Li","sequence":"additional","affiliation":[{"name":"Taiyuan University of Technology,College of Computer Science and Technology,China"}]},{"given":"Peini","family":"Guo","sequence":"additional","affiliation":[{"name":"Peking University,Shenzhen Graduate School,National Key Laboratory of General Artificial Intelligence,China"}]},{"given":"Guoquan","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,Shenzhen Graduate School,National Key Laboratory of General Artificial Intelligence,China"}]},{"given":"Ti","family":"Wang","sequence":"additional","affiliation":[{"name":"Peking University,Shenzhen Graduate School,National Key Laboratory of General Artificial Intelligence,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956592"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2023.3279689"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/s21227665"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2022.07.012"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2987728"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00056"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859836"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956730"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20500-2_26"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1981.1163530"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/app12010327"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01330"},{"key":"ref22","article-title":"MSAF: Multimodal split attention fusion","author":"Su","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956589"},{"issue":"11","key":"ref24","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Van 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\/10447640.pdf?arnumber=10447640","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:54:03Z","timestamp":1722578043000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447640\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447640","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}