{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T21:27:38Z","timestamp":1770845258046,"version":"3.50.1"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T00:00:00Z","timestamp":1759622400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,5]]},"DOI":"10.1109\/smc58881.2025.11342953","type":"proceedings-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T20:54:44Z","timestamp":1769633684000},"page":"75-79","source":"Crossref","is-referenced-by-count":0,"title":["Audio-Visual Cross-Attention for Improved Deepfake Video Detection and Forgery Localization"],"prefix":"10.1109","author":[{"given":"Oussama","family":"Jalleli","sequence":"first","affiliation":[{"name":"INRS-EMT, Université du Québec,Montreal,QC,Canada"}]},{"given":"Yi","family":"Zhu","sequence":"additional","affiliation":[{"name":"INRS-EMT, Université du Québec,Montreal,QC,Canada"}]},{"given":"Tiago H.","family":"Falk","sequence":"additional","affiliation":[{"name":"INRS-EMT, Université du Québec,Montreal,QC,Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.02559","article-title":"Avff: Audio-visual feature fusion for video deepfake detection","author":"Oorloff","year":"2024"},{"key":"ref2","article-title":"Dimodif: Discourse modalityinformation differentiation for audio-visual deepfake detection and localization","author":"Koutlis"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00837"},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00009","article-title":"Faceforensics++: Learning to detect manipulated facial images","author":"R\u00f6ssler","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-659"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2168"},{"key":"ref8","article-title":"Xls-r: Self-supervised cross-lingual speech representation learning at scale","author":"Babu","year":"2021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3285283"},{"key":"ref10","article-title":"Does audio deepfake detection generalize?","volume-title":"Interspeech","author":"M\u00fcller"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/IJCNN60899.2024.10650962","article-title":"Mlaad: The multi-language audio anti-spoofing dataset","volume-title":"International Joint Conference on Neural Networks (IJCNN)","author":"M\u00fcller"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103818"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.00476","article-title":"Mvitv2: Improved multiscale vision transformers for classification and detection","author":"Li","year":"2022"},{"key":"ref14","doi-asserted-by":"crossref","article-title":"Bsn++: Complementary boundary regressor with scale-balanced relation modeling for temporal action proposal generation","author":"Su","DOI":"10.1609\/aaai.v35i3.16363"},{"key":"ref15","article-title":"wav2vec 2.0:A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1820"},{"key":"ref17","article-title":"Avff: Audio-visual deepfake detection with fine-grained forgery localization","author":"Hua","year":"2023","journal-title":"CVPR"}],"event":{"name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","location":"Vienna, Austria","start":{"date-parts":[[2025,10,5]]},"end":{"date-parts":[[2025,10,8]]}},"container-title":["2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11342430\/11342431\/11342953.pdf?arnumber=11342953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:50:19Z","timestamp":1770843019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342953\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/smc58881.2025.11342953","relation":{},"subject":[],"published":{"date-parts":[[2025,10,5]]}}}