{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T15:32:20Z","timestamp":1784302340319,"version":"3.55.0"},"reference-count":67,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["2022YFB3103504"],"award-info":[{"award-number":["2022YFB3103504"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017610","name":"Shenzhen Science and Technology Program","doi-asserted-by":"publisher","award":["20220016"],"award-info":[{"award-number":["20220016"]}],"id":[{"id":"10.13039\/501100017610","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62261160653"],"award-info":[{"award-number":["62261160653"]}],"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":["62122032"],"award-info":[{"award-number":["62122032"]}],"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":["62172359"],"award-info":[{"award-number":["62172359"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans.Inform.Forensic Secur."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tifs.2023.3262148","type":"journal-article","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T18:43:56Z","timestamp":1679942636000},"page":"2015-2029","source":"Crossref","is-referenced-by-count":178,"title":["AVoiD-DF: Audio-Visual Joint Learning for Detecting Deepfake"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0046-5994","authenticated-orcid":false,"given":"Wenyuan","family":"Yang","sequence":"first","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhikai","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhuque Laboratory, Tencent Security, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bofei","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0921-8869","authenticated-orcid":false,"given":"Zhongjie","family":"Ba","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6860-647X","authenticated-orcid":false,"given":"Zhihua","family":"Xia","sequence":"additional","affiliation":[{"name":"College of Cyber Security, Jinan University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7141-708X","authenticated-orcid":false,"given":"Xiaochun","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Sun Yat-sen University, Shenzhen Campus, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1969-2591","authenticated-orcid":false,"given":"Kui","family":"Ren","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01475"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414670"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475508"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3045937"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.397"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref13","first-page":"1","article-title":"Transfer learning from speaker verification to multispeaker text-to-speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jia"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1111"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref17","article-title":"Unsupervised audiovisual synthesis via exemplar autoencoders","author":"Deng","year":"2020","journal-title":"arXiv:2001.04463"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3093446"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00111"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146781"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/ASVSPOOF.2021-8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2249"},{"key":"ref25","article-title":"AASIST: Audio anti-spoofing using integrated spectro-temporal graph attention networks","author":"Jung","year":"2021","journal-title":"arXiv:2110.01200"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-16"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2019.8918703"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1982"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6044"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2999185"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531415"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3625231"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00338"},{"key":"ref36","article-title":"A better use of audio-visual cues: Dense video captioning with bi-modal transformer","author":"Iashin","year":"2020","journal-title":"arXiv:2005.08271"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16403"},{"key":"ref38","first-page":"11449","article-title":"Exploring cross-video and cross-modality signals for weakly-supervised audio-visual video parsing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69544-6_17"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01047"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00694"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053895"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3137649"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3057230"},{"key":"ref45","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref49","article-title":"DeepFakes: A new threat to face recognition? Assessment and detection","author":"Korshunov","year":"2018","journal-title":"arXiv:1812.08685"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"issue":"2","key":"ref51","first-page":"3","article-title":"Contributing data to deepfake detection research","volume":"1","author":"Dufour","year":"2019","journal-title":"Google AI Blog"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2020.101114"},{"key":"ref55","article-title":"The deepfake detection challenge (DFDC) preview dataset","author":"Dolhansky","year":"2019","journal-title":"arXiv:1910.08854"},{"key":"ref56","first-page":"1","article-title":"FakeAVCeleb: A novel audio-video multimodal deepfake dataset","volume-title":"Proc. Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Khalid"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01793-3_21"},{"key":"ref58","article-title":"DeepFaceLab: Integrated, flexible and extensible face-swapping framework","author":"Perov","year":"2020","journal-title":"arXiv:2005.05535"},{"key":"ref59","article-title":"The DeepFake detection challenge (DFDC) dataset","author":"Dolhansky","year":"2020","journal-title":"arXiv:2006.07397"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683713"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref62","article-title":"Use of a capsule network to detect fake images and videos","author":"Nguyen","year":"2019","journal-title":"arXiv:1910.12467"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2019.00020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428361"},{"key":"ref65","article-title":"Deepfake video detection using convolutional vision transformer","author":"Wodajo","year":"2021","journal-title":"arXiv:2102.11126"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"}],"container-title":["IEEE Transactions on Information Forensics and Security"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10206\/9970396\/10081373.pdf?arnumber=10081373","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T18:36:41Z","timestamp":1707849401000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10081373\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/tifs.2023.3262148","relation":{},"ISSN":["1556-6013","1556-6021"],"issn-type":[{"value":"1556-6013","type":"print"},{"value":"1556-6021","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}