{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:29:38Z","timestamp":1775230178254,"version":"3.50.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["2021ZD0112100"],"award-info":[{"award-number":["2021ZD0112100"]}]},{"DOI":"10.13039\/501100001809","name":"National NSF of China","doi-asserted-by":"publisher","award":["62336001"],"award-info":[{"award-number":["62336001"]}],"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":["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"}]},{"name":"Beijing NSF","award":["4222014"],"award-info":[{"award-number":["4222014"]}]},{"name":"Rapid-Rich Object Search (ROSE) Laboratory, Nanyang Technological University, Singapore"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcsvt.2023.3309899","type":"journal-article","created":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T17:59:39Z","timestamp":1693331979000},"page":"6926-6936","source":"Crossref","is-referenced-by-count":36,"title":["PVASS-MDD: Predictive Visual-Audio Alignment Self-Supervision for Multimodal Deepfake Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5204-2929","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"first","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3940-207X","authenticated-orcid":false,"given":"Xiaolong","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5096-8752","authenticated-orcid":false,"given":"Rongrong","family":"Ni","sequence":"additional","affiliation":[{"name":"Institute of Information Science, Beijing Jiaotong University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4681-0431","authenticated-orcid":false,"given":"Siyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Rapid-Rich Object Search Laboratory, Interdisciplinary Graduate Program, Nanyang Technological University, Jurong West, Singapore"}]},{"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6262-8125","authenticated-orcid":false,"given":"Alex C.","family":"Kot","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Nanyang Technological University, Jurong West, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3244786"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157444"},{"key":"ref4","volume-title":"Faceswap","year":"2020"},{"key":"ref5","volume-title":"Deepfakes","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1137"},{"key":"ref10","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023","journal-title":"arXiv:2301.12503"},{"key":"ref11","article-title":"ArchiSound: Audio generation with diffusion","author":"Schneider","year":"2023","journal-title":"arXiv:2301.13267"},{"key":"ref12","article-title":"SampleRNN: An unconditional end-to-end neural audio generation model","author":"Mehri","year":"2016","journal-title":"arXiv:1612.07837"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2019.2945210"},{"key":"ref14","first-page":"3325","article-title":"Audeo: Audio generation for a silent performance video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Su"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3238517"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3239607"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3278310"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3133859"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3209336"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3281448"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3249566"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475508"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1085"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2019.8918703"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1982"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747766"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3079897"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16302"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref42","article-title":"Unsupervised audiovisual synthesis via exemplar autoencoders","volume-title":"arXiv:2001.04463","author":"Deng","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3262148"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3625231"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01011"},{"key":"ref48","first-page":"46","article-title":"Exposing deepfake videos by detecting face warping artifacts","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Li"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2019.00020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3453892.3453893"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01953"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-2079"},{"key":"ref57","article-title":"SP-SEDT: Self-supervised pre-training for sound event detection transformer","author":"Ye","year":"2021","journal-title":"arXiv:2111.15222"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"ref59","article-title":"Real face foundation representation learning for generalized deepfake detection","author":"Shi","year":"2023","journal-title":"arXiv:2303.08439"},{"key":"ref60","article-title":"Self-supervised transformer for deepfake detection","author":"Zhao","year":"2022","journal-title":"arXiv:2203.01265"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.11.001"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350899"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3536426"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref67","article-title":"The deepfake detection challenge (DFDC) preview dataset","author":"Dolhansky","year":"2019","journal-title":"arXiv:1910.08854"},{"key":"ref68","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":"ref69","article-title":"Deepfake video detection using convolutional vision transformer","author":"Wodajo","year":"2021","journal-title":"arXiv:2102.11126"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01815"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10634006\/10233898.pdf?arnumber=10233898","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:12:27Z","timestamp":1736453547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10233898\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":70,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3309899","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}