{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:02:28Z","timestamp":1787788948902,"version":"build-2784847793"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T00:00:00Z","timestamp":1716768000000},"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":[[2024,5,27]]},"DOI":"10.1109\/fg59268.2024.10581998","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T17:40:08Z","timestamp":1720719608000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Dynamic Cross Attention for Audio-Visual Person Verification"],"prefix":"10.1109","author":[{"given":"R. Gnana","family":"Praveen","sequence":"first","affiliation":[{"name":"Computer Research Institute of Montreal (CRIM),Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jahangir","family":"Alam","sequence":"additional","affiliation":[{"name":"Computer Research Institute of Montreal (CRIM),Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2015.2462851"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3084299"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.081"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_31"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095234"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-48312-7_2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3165180"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667055"},{"key":"ref12","article-title":"Cross-attentional audio-visual fusion for weakly-supervised action localization","volume-title":"International Conference on Learning Representations","author":"Lee"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2022.3233083"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00089"},{"key":"ref16","article-title":"Cross-attention is not always needed: Dynamic cross-attention for audio-visual dimensional emotion recognition","author":"Praveen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114794"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2229"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3057230"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/odyssey.2020-37"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2020-41"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414260"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683477"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00074"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/EUVIP53989.2022.9922810"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095883"},{"key":"ref27","article-title":"When does label smoothing help?","volume":"32","author":"M\u00fcller","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","first-page":"5115","article-title":"Regularizing deep neural networks by noise: its interpretation and optimization","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Noh"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-993"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3206541"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2005.08.001"},{"key":"ref33","article-title":"Voxsrc 2020: The second voxceleb speaker recognition challenge","author":"Nagrani","year":"2020","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096814"}],"event":{"name":"2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)","location":"Istanbul, Turkiye","start":{"date-parts":[[2024,5,27]]},"end":{"date-parts":[[2024,5,31]]}},"container-title":["2024 IEEE 18th International Conference on Automatic Face and Gesture Recognition (FG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10581880\/10581860\/10581998.pdf?arnumber=10581998","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,17]],"date-time":"2024-07-17T04:56:57Z","timestamp":1721192217000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10581998\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,27]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/fg59268.2024.10581998","relation":{},"subject":[],"published":{"date-parts":[[2024,5,27]]}}}