{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T17:01:29Z","timestamp":1783530089325,"version":"3.55.0"},"reference-count":95,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["2022YFB3104700"],"award-info":[{"award-number":["2022YFB3104700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2028"],"award-info":[{"award-number":["U23B2028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62121002"],"award-info":[{"award-number":["62121002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62232006"],"award-info":[{"award-number":["62232006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032006"],"award-info":[{"award-number":["62032006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472395"],"award-info":[{"award-number":["62472395"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272436"],"award-info":[{"award-number":["62272436"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcsvt.2024.3524602","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T14:49:28Z","timestamp":1735656568000},"page":"4698-4712","source":"Crossref","is-referenced-by-count":4,"title":["Distilling Multi-Level Semantic Cues Across Multi-Modalities for Face Forgery Detection"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6403-761X","authenticated-orcid":false,"given":"Lingyun","family":"Yu","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0381-8695","authenticated-orcid":false,"given":"Tian","family":"Xie","sequence":"additional","affiliation":[{"name":"AHU-IAI AI Joint Laboratory, Anhui University, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanbin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7108-9159","authenticated-orcid":false,"given":"Guoqing","family":"Jin","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Communication Content Cognition, People&#x2019;s Daily Online, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9591-8601","authenticated-orcid":false,"given":"Zhiguo","family":"Ding","sequence":"additional","affiliation":[{"name":"Third Research Institute of Ministry of Public Security, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-5315","authenticated-orcid":false,"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref2","volume-title":"Deepfakes","year":"2020"},{"key":"ref3","volume-title":"Faceswap","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00639"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414670"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00582"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639163"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/BTAS46853.2019.9185974"},{"issue":"1","key":"ref13","first-page":"80","article-title":"Recurrent convolutional strategies for face manipulation detection in videos","volume":"3","author":"Sabir","year":"2019","journal-title":"Interfaces"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3074259"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3217950"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3182509"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237169"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301242"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"ref21","article-title":"ForensicTransfer: Weakly-supervised domain adaptation for forgery detection","author":"Cozzolino","year":"2018","journal-title":"arXiv:1812.02510"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/102"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00872"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00295"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01475"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107950"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3238517"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3209336"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3237322"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19830-4_27"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"ref36","article-title":"Delving into sequential patches for deepfake detection","author":"Guan","year":"2022","journal-title":"arXiv:2207.02803"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475508"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3625231"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01468"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3330390"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_23"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3233774"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3198275"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3119403"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3214768"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3239607"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00703"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531415"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2024.3516561"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3332218"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3169921"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00858"},{"key":"ref61","article-title":"Spatio-temporal features for generalized detection of deepfake videos","author":"Ganiyusufoglu","year":"2020","journal-title":"arXiv:2010.11844"},{"key":"ref62","article-title":"Deepfake detection using spatiotemporal convolutional networks","author":"de Lima","year":"2020","journal-title":"arXiv:2006.14749"},{"key":"ref63","article-title":"Multimodal graph learning for deepfake detection","author":"Yan","year":"2022","journal-title":"arXiv:2209.05419"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312738"},{"key":"ref65","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014","journal-title":"arXiv:1412.6550"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_7"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref69","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhan"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00765"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123359"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref74","article-title":"Exposing DeepFake videos by detecting face warping artifacts","author":"Li","year":"2018","journal-title":"arXiv:1811.00656"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01647"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00114"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3292039"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"ref80","article-title":"The DeepFake detection challenge (DFDC) dataset","author":"Dolhansky","year":"2020","journal-title":"arXiv:2006.07397"},{"key":"ref81","article-title":"RetinaFace: Single-stage dense face localisation in the wild","author":"Deng","year":"2019","journal-title":"arXiv:1905.00641"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref83","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref85","article-title":"Video Swin transformer","author":"Liu","year":"2021","journal-title":"arXiv:2106.13230"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref88","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"ref91","article-title":"Masked autoencoders as spatiotemporal learners","author":"Feichtenhofer","year":"2022","journal-title":"arXiv:2205.09113"},{"key":"ref92","article-title":"MViTv2: Improved multiscale vision transformers for classification and detection","author":"Li","year":"2021","journal-title":"arXiv:2112.01526"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref94","first-page":"4694","article-title":"When does label smoothing help","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"M\u00fcller"},{"key":"ref95","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 Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10989278\/10819430.pdf?arnumber=10819430","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:37Z","timestamp":1767638497000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10819430\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":95,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3524602","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}