{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T16:17:26Z","timestamp":1784391446682,"version":"3.55.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0212000"],"award-info":[{"award-number":["2024YFE0212000"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471420"],"award-info":[{"award-number":["62471420"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024M761497"],"award-info":[{"award-number":["2024M761497"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Technology Commissioned Development Project of Nanjing University of Posts and Telecommunications","award":["2025Y234"],"award-info":[{"award-number":["2025Y234"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tifs.2026.3674401","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:13:58Z","timestamp":1773692038000},"page":"3353-3365","source":"Crossref","is-referenced-by-count":1,"title":["FauForensics: Boosting Audio-Visual Deepfake Detection With Facial Action Units"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2214-238X","authenticated-orcid":false,"given":"Jian","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and the State Key Laboratory of Tibetan Intelligent Information Processing and Application, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2183-5990","authenticated-orcid":false,"given":"Baoyuan","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4497-0135","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5512-6984","authenticated-orcid":false,"given":"Qingshan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and the State Key Laboratory of Tibetan Intelligent Information Processing and Application, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLPRO.2025.3530270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78341-8_12"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02559"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02128-1"},{"key":"ref6","article-title":"Understanding audiovisual deepfake detection: Techniques, challenges, human factors and perceptual insights","author":"Hashmi","year":"2024","journal-title":"arXiv:2411.07650"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpnec.2023.100187"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980255"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2025.3554477"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3309899"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312738"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447248"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3625100"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3169921"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3186803"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3249566"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02048"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3520001"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3045937"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00521"},{"key":"ref24","article-title":"LatentSync: Taming audio-conditioned latent diffusion models for lip sync with SyncNet supervision","author":"Li","year":"2024","journal-title":"arXiv:2412.09262"},{"key":"ref25","article-title":"Loopy: Taming audio-driven portrait avatar with long-term motion dependency","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jiang"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9980296"},{"key":"ref28","article-title":"FakeOut: Leveraging out-of-domain self-supervision for multi-modal video deepfake detection","author":"Knafo","year":"2022","journal-title":"arXiv:2212.00773"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00101"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00106"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00338"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2892"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3381823"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3205562"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02367"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2749299"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475508"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00049"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3239223"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3409054"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69449-4_13"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01011"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3625231"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00435"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262148"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2735"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i1.31982"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755455"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547754"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref53","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/173"},{"key":"ref56","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.4"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref59","article-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset","author":"Khalid","year":"2021","journal-title":"arXiv:2108.05080"},{"key":"ref60","article-title":"Detecting lip-syncing deepfakes: Vision temporal transformer for analyzing mouth inconsistencies","author":"Datta","year":"2025","journal-title":"arXiv:2504.01470"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01793-3_21"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-1"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095247"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2025.3618409"},{"key":"ref68","article-title":"AdamP: Slowing down the slowdown for momentum optimizers on scale-invariant weights","author":"Heo","year":"2020","journal-title":"arXiv:2006.08217"},{"key":"ref69","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"issue":"11","key":"ref71","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10206\/11313711\/11435467.pdf?arnumber=11435467","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T20:04:55Z","timestamp":1775678695000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11435467\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tifs.2026.3674401","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}