{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:40Z","timestamp":1775230180044,"version":"3.50.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["2020AAA0140003"],"award-info":[{"award-number":["2020AAA0140003"]}]},{"DOI":"10.13039\/501100001809","name":"National NSF of China","doi-asserted-by":"publisher","award":["U1936212"],"award-info":[{"award-number":["U1936212"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National NSF of China","doi-asserted-by":"publisher","award":["62120106009"],"award-info":[{"award-number":["62120106009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003091","name":"NSF of Shandong Province","doi-asserted-by":"crossref","award":["ZR2022LZH011"],"award-info":[{"award-number":["ZR2022LZH011"]}],"id":[{"id":"10.13039\/501100003091","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tcsvt.2023.3312738","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T17:45:21Z","timestamp":1694108721000},"page":"2803-2813","source":"Crossref","is-referenced-by-count":34,"title":["MCL: Multimodal Contrastive Learning for Deepfake Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3940-207X","authenticated-orcid":false,"given":"Xiaolong","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5204-2929","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6111-9000","authenticated-orcid":false,"given":"Xiaolong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8581-9554","authenticated-orcid":false,"given":"Yao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref2","article-title":"FaceShifter: Towards high fidelity and occlusion aware face swapping","author":"Li","year":"2019","journal-title":"arXiv:1912.13457"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3220630"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2804768"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2014.2347513"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3123829"},{"key":"ref8","article-title":"The DeepFake detection challenge (DFDC) dataset","author":"Dolhansky","year":"2020","journal-title":"arXiv:2006.07397"},{"key":"ref9","first-page":"1","article-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Khalid"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00295"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107950"},{"key":"ref14","article-title":"Exposing DeepFake videos by detecting face warping artifacts","author":"Li","year":"2018","journal-title":"arXiv:1811.00656"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414034"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639163"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00555"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3237322"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00304"},{"key":"ref30","article-title":"Dataset augmentation in feature space","author":"DeVries","year":"2017","journal-title":"arXiv:1702.05538"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3161427"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531937"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2023.3269303"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01468"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00876"},{"key":"ref37","article-title":"DeepFakes: A new threat to face recognition? Assessment and detection","author":"Korshunov","year":"2018","journal-title":"arXiv:1812.08685"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413769"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3449978"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00572"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00434"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01057"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2019.00020"},{"key":"ref47","article-title":"FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces","author":"Wang","year":"2019","journal-title":"arXiv:1909.06122"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475508"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3182509"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3009287"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3269841"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3238517"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3239607"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3217950"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3281448"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3209336"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16193"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531415"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262148"},{"key":"ref60","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref62","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref63","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref64","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref65","volume-title":"Faceswap [EB\/OL]","year":"2020"},{"key":"ref66","article-title":"DeepFaceLab: Integrated, flexible and extensible face-swapping framework","author":"Perov","year":"2020","journal-title":"arXiv:2005.05535"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00728"},{"key":"ref68","first-page":"1","article-title":"First order motion model for image animation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Siarohin"},{"key":"ref69","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020","journal-title":"arXiv:2002.10137"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3625231"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref75","first-page":"5210","article-title":"AutoVC: Zero-shot voice style transfer with only autoencoder loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Qian"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10078"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10492617\/10243082.pdf?arnumber=10243082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:52:31Z","timestamp":1712692351000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10243082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":77,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3312738","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}