{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:30Z","timestamp":1777890090544,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100022246","name":"National Supercomputing Centre, Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100022246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01283","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13826-13836","source":"Crossref","is-referenced-by-count":0,"title":["Intra-Modal and Cross-Modal Synchronization for Audio-Visual Deepfake Detection and Temporal Localization"],"prefix":"10.1109","author":[{"given":"Ashutosh","family":"Anshul","sequence":"first","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shreyas","family":"Gopal","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepu","family":"Rajan","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2889052"},{"key":"ref2","article-title":"Detecting audio-visual deepfakes with fine-grained inconsistencies","author":"Astrid","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Layer normalization","author":"Ba","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5220\/0010832700003124"},{"key":"ref5","first-page":"1","article-title":"The truncated normal distribution","author":"Burkardt","year":"2014","journal-title":"Department of Scientific Computing Website, Florida State University"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref8","article-title":"Avdeepfake 1 m: A large-scale 11 m -driven audio-visual deepfake dataset","author":"Cai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103818"},{"key":"ref10","article-title":"Audio-visual synchronisation in the wild","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC63619.2025.10848944"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3625231"},{"key":"ref13","article-title":"Exploiting style latent flows for generalizing deepfake detection video detection","author":"Choi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01483"},{"key":"ref17","volume-title":"The deepfake detection challenge (dfdc) dataset","author":"Dolhansky","year":"2020"},{"key":"ref18","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3536426"},{"key":"ref21","article-title":"Contrastive audio-visual masked autoencoder","author":"Gong","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19954"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01453"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19990"},{"key":"ref27","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume":"31","author":"Jia","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Fakeavceleb: A novel audio-video multimodal deepfake dataset","author":"Khalid","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Dftransfusion: Multimodal deepfake detection via lip-audio cross-attention and facial self-attention","author":"Kharel","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.397"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01057"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00808"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00728"},{"key":"ref39","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02559"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3239607"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref44","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16363"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2024.3433596"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26701"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00402"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02071"},{"key":"ref52","article-title":"Towards generalizable deepfake video detection with thumbnail layout and graph reasoning","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262148"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_24"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613767"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447248"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444401.pdf?arnumber=11444401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:32Z","timestamp":1777613372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444401\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01283","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}