{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:18:51Z","timestamp":1778048331881,"version":"3.51.4"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00251","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"2553-2563","source":"Crossref","is-referenced-by-count":0,"title":["A-V Representation Learning via Audio Shift Prediction for Multimodal Deepfake Detection and Temporal Localization"],"prefix":"10.1109","author":[{"given":"Ashutosh","family":"Anshul","sequence":"first","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eng Siong","family":"Chng","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepu","family":"Rajan","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,College of Computing and Data Science,Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Detecting audio-visual deepfakes with fine-grained inconsistencies","author":"Astrid","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5220\/0010832700003124"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680795"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103818"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00150"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3625231"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01483"},{"key":"ref12","article-title":"The deepfake detection challenge (dfdc) dataset","author":"Dolhansky","year":"2020"},{"key":"ref13","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01011"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3536426"},{"key":"ref16","article-title":"Contrastive audio-visual masked autoencoder","author":"Gong","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19990"},{"key":"ref22","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":"ref23","article-title":"Fakeavceleb: A novel audio-video multimodal deep-fake dataset","author":"Khalid","year":"2021"},{"key":"ref24","article-title":"Df-transfusion: Multimodal deepfake detection via lip-audio cross-attention and facial self-attention","author":"Kharel","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.397"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01057"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01591"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00399"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312738"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01647"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3521766"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00728"},{"key":"ref35","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02559"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3385286"},{"key":"ref39","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00106"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01808"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16363"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095247"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02657"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref47","article-title":"Fau-forensics: Boosting audio-visual deepfake detection with facial action units","author":"Wang","year":"2025"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/lsp.2024.3433596"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26701"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00402"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995566"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02071"},{"key":"ref53","article-title":"Towards generalizable deepfake video detection with thumbnail layout and graph reasoning","author":"Xu","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00858"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262148"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3309899"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237322"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613767"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447248"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492005.pdf?arnumber=11492005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:53:32Z","timestamp":1778046812000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492005\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00251","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}