{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T18:08:34Z","timestamp":1783534114016,"version":"3.55.0"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0112100"],"award-info":[{"award-number":["2021ZD0112100"]}],"id":[{"id":"10.13039\/501100012166","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"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3281448","type":"journal-article","created":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T17:27:24Z","timestamp":1685467644000},"page":"4462-4471","source":"Crossref","is-referenced-by-count":49,"title":["MSVT: Multiple Spatiotemporal Views Transformer for DeepFake Video Detection"],"prefix":"10.1109","volume":"33","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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fen","family":"Xia","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Company Ltd., Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Jiang","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Company Ltd., Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"Mashang Consumer Finance Company Ltd., Chongqing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref12","first-page":"46","article-title":"Exposing deepfake videos by detecting face warping artifacts","author":"li","year":"2019","journal-title":"Proc IEEE Conf Comp Vis Pattern Recognit"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00033"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803661"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref53","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"b brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Sys"},{"key":"ref52","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2019.00020"},{"key":"ref55","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc 16th Eur Conf Comput Vis (ECCV)"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2804768"},{"key":"ref54","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682602"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref19","article-title":"FakeSpotter: A simple yet robust baseline for spotting AI-synthesized fake faces","author":"wang","year":"2019","journal-title":"arXiv 1909 06122"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00765"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3074259"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413707"},{"key":"ref46","article-title":"Combining EfficientNet and vision transformers for video deepfake detection","author":"coccomini","year":"2021","journal-title":"arXiv 2107 02612"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414225"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00213"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00152"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19954"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01475"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16193"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3009287"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3189545"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2993004"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3220630"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2473436"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/102"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19955"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414034"},{"key":"ref31","first-page":"5037","article-title":"Lips don’t lie: A generalisable and robust approach to face forgery detection","author":"haliassos","year":"2021","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2016.2603342"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2999185"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413769"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475508"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"ref76","first-page":"1755","article-title":"Dlib-ml: A machine learning toolkit","volume":"10","author":"king","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref2","year":"2020","journal-title":"Deepfake"},{"key":"ref1","year":"2020","journal-title":"Faceswap"},{"key":"ref39","article-title":"Discriminative feature mining based on frequency information and metric learning for face forgery detection","author":"li","year":"2021","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746061"},{"key":"ref71","author":"dufour","year":"2019","journal-title":"Contributing data to deepfake detection research"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5724-z"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"ref72","article-title":"The deepfake detection challenge (DFDC) dataset","author":"dolhansky","year":"2020","journal-title":"arXiv 2006 07397"},{"key":"ref24","article-title":"Spatio-temporal features for generalized detection of deepfake videos","author":"ganiyusufoglu","year":"2020","journal-title":"arXiv 2010 11844"},{"key":"ref68","article-title":"Gaussian error linear units (GELUs)","author":"hendrycks","year":"2016","journal-title":"arXiv 1606 08415"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19778-9_41"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/178"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190655"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.732"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803740"},{"key":"ref64","article-title":"Self-supervised transformer for deepfake detection","author":"zhao","year":"2022","journal-title":"arXiv 2203 01265"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03867-9"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3239223"},{"key":"ref21","first-page":"3247","article-title":"Leveraging frequency analysis for deep fake image recognition","author":"frank","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref65","article-title":"Delving into sequential patches for deepfake detection","author":"guan","year":"2022","journal-title":"arXiv 2207 02803"},{"key":"ref28","first-page":"80","article-title":"Recurrent convolutional strategies for face manipulation detection in videos","volume":"3","author":"sabir","year":"2019","journal-title":"Interfaces (GUI)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639163"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01939"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531415"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01692"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10138555.pdf?arnumber=10138555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T18:42:36Z","timestamp":1695667356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10138555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":78,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3281448","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}