{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T17:39:02Z","timestamp":1778002742752,"version":"3.51.4"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Joint Funds of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20300"],"award-info":[{"award-number":["U23A20300"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tce.2025.3599517","type":"journal-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:43:26Z","timestamp":1755546206000},"page":"10893-10905","source":"Crossref","is-referenced-by-count":1,"title":["Share Token Tensorized Attention Fusion: Enhancing Audio-Visual Emotion Recognition for Consumer Electronics"],"prefix":"10.1109","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-8953-4142","authenticated-orcid":false,"given":"Haixv","family":"Lu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Hainan University, Haikou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5233-9637","authenticated-orcid":false,"given":"Debin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7986-4244","authenticated-orcid":false,"given":"Laurence T.","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7479-585X","authenticated-orcid":false,"given":"Ruonan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shijie","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Engineering, The University of Warwick, Coventry, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4919-3274","authenticated-orcid":false,"given":"Xiaosong","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Hainan University, Haikou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3318150"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3308209"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2021.3062802"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2021.3056421"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3236972"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2023.3263672"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-205154"},{"key":"ref8","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. naacL-HLT","volume":"1","author":"Kenton"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3001969"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7965918"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12112436"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00609"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00232"},{"key":"ref14","article-title":"MTCAE-DFER: Multi-task cascaded autoencoder for dynamic facial expression recognition","author":"Xiang","year":"2024","journal-title":"arXiv:2412.18988"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.11.020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2010.02.001"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28715"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27950"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1209"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref22","first-page":"1","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Jaderberg"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01957"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icassp43922.2022.9746613"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref29","first-page":"1","article-title":"A tensorized transformer for language modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ma"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.858"},{"key":"ref31","article-title":"Tensor product attention is all you need","author":"Zhang","year":"2025","journal-title":"arXiv:2501.06425"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289464"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16465"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956592"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.1188976"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref38","article-title":"VANPY: Voice analysis framework","author":"Koushnir","year":"2025","journal-title":"arXiv:2502.17579"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3436913"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612365"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25075-0_11"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_18"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/app12010327"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-021-03529-7"},{"key":"ref45","article-title":"Multimodal emotion recognition using audio-video transformer fusion with cross attention","author":"Venkatraman","year":"2024","journal-title":"arXiv:2407.18552"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193151"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102382"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.197"},{"key":"ref49","article-title":"AffectGPT: A new dataset, model, and benchmark for emotion understanding with multimodal large language models","author":"Lian","year":"2025","journal-title":"arXiv:2501.16566"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00628"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548137"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2023.3282410"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.391"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556630"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.09.027"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11306167\/11128871.pdf?arnumber=11128871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:42:08Z","timestamp":1766428928000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":55,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tce.2025.3599517","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"value":"0098-3063","type":"print"},{"value":"1558-4127","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}