{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:16:22Z","timestamp":1774419382522,"version":"3.50.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889666","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["TDMER: A Task-Driven Method for Multimodal Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Qian","family":"Xu","sequence":"first","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Gu","sequence":"additional","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyu","family":"Li","sequence":"additional","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwest University,School of Journalism and Communication,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hai-Xiang","family":"Lin","sequence":"additional","affiliation":[{"name":"Delft University of Technology,Delft Institute of Applied Mathematics,Delft,The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linsong","family":"Liu","sequence":"additional","affiliation":[{"name":"Xidian University,School of Artificial Intelligence,Xi’an,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3188390"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2023.3254179"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.006"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.532279"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s40846-019-00505-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3205919"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"ref11","first-page":"4835","article-title":"Deep multimodal fusion by channel exchanging","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1190"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00804"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00278"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3420937"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3147546"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611704"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2021.2000688"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"ref25","article-title":"Cross-modality fusion transformer for multispectral object detection","author":"Qingyun","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"ref27","article-title":"Central moment discrepancy (cmd) for domain-invariant representation learning","author":"Zellinger","year":"2017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746924"},{"key":"ref29","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","article-title":"Addressing failure prediction by learning model confidence","volume":"32","author":"Corbi\u00e8re","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02005"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref36","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57077-4_10"},{"key":"ref38","article-title":"Learning factorized multimodal representations","author":"Tsai","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.421"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889666.pdf?arnumber=10889666","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:35Z","timestamp":1774416155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889666\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889666","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}