{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:32:39Z","timestamp":1780356759910,"version":"3.54.1"},"reference-count":19,"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\/icasspw62465.2024.10626511","type":"proceedings-article","created":{"date-parts":[[2024,8,15]],"date-time":"2024-08-15T17:19:18Z","timestamp":1723742358000},"page":"309-313","source":"Crossref","is-referenced-by-count":2,"title":["A Cross-Attention Emotion Recognition Algorithm Based on Audio and Video Modalities"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Wu","sequence":"first","affiliation":[{"name":"Automation School of Qingdao University,Qingdao,China,266000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuan","family":"Mu","sequence":"additional","affiliation":[{"name":"Automation School of Qingdao University,Qingdao,China,266000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Qi","sequence":"additional","affiliation":[{"name":"South China University of Technology,School of Future Technology,Guangzhou,China,511436"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaorui","family":"Liu","sequence":"additional","affiliation":[{"name":"Automation School of Qingdao University,Qingdao,China,266000"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"41","article-title":"An empirical study of the naive Bayes classifier [C]","volume-title":"Proceedings of the 2001 Workshop on Empirical Methods in Artificial Intelligence","author":"Rish"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.095"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"issue":"04","key":"ref5","first-page":"192","article-title":"Speech and text bimodal emotion recognition model combined with Bi-LSTM-CNN [J]","volume":"58","author":"Wang","year":"2012","journal-title":"Journal of Computer Engineering and Application"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CODIS.2012.6422274"},{"issue":"03","key":"ref7","first-page":"889","article-title":"Facial expression recognition based on local Features and two-stage attention weight learning [J]","volume":"39","author":"Zheng","year":"2022","journal-title":"Applied Research of Computers"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2997632"},{"issue":"1","key":"ref9","first-page":"48","article-title":"Research on Bimodal Emotion Recognition Based on Facial expression and speech [J]","volume":"40","author":"Wang","year":"2014","journal-title":"Information Research"},{"key":"ref10","first-page":"1","article-title":"Multi-task Multi-modal Sentiment Analysis Model Based on Perception Fusion [J\/OL]","author":"Wu","journal-title":"Data Analysis and Knowledge Discovery"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2764438"},{"issue":"10","key":"ref12","first-page":"1889","article-title":"Research on emotion recognition method based on audio and video [J]","volume":"37","author":"Lin","year":"2021","journal-title":"Signal Processing"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11571-020-09591-9"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.22606\/fsp.2020.41006"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2654543"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2018.12.008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"ref18","article-title":"Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos[OL]","author":"Zadeh","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2744-2"}],"event":{"name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10625769\/10625780\/10626511.pdf?arnumber=10626511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,16]],"date-time":"2024-08-16T05:49:47Z","timestamp":1723787387000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10626511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icasspw62465.2024.10626511","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}