{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T22:09:50Z","timestamp":1773180590649,"version":"3.50.1"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,25]],"date-time":"2023-09-25T00:00:00Z","timestamp":1695600000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,25]]},"DOI":"10.1109\/ijcb57857.2023.10449301","type":"proceedings-article","created":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T18:31:14Z","timestamp":1709317874000},"page":"1-11","source":"Crossref","is-referenced-by-count":7,"title":["Unmasking Deepfakes: Masked Autoencoding Spatiotemporal Transformers for Enhanced Video Forgery Detection"],"prefix":"10.1109","author":[{"given":"Sayantan","family":"Das","sequence":"first","affiliation":[{"name":"Queen’s University,Canada"}]},{"given":"Mojtaba","family":"Kolahdouzi","sequence":"additional","affiliation":[{"name":"Queen’s University,Canada"}]},{"given":"Levent","family":"\u00d6zparlak","sequence":"additional","affiliation":[{"name":"Irdeto BV"}]},{"given":"Will","family":"Hickie","sequence":"additional","affiliation":[{"name":"Irdeto BV"}]},{"given":"Ali","family":"Etemad","sequence":"additional","affiliation":[{"name":"Queen’s University,Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00152"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2909827.2930786"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2021.03.005"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16193"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3009287"},{"key":"ref12","article-title":"MMFlow: Openmmlab optical flow toolbox and benchmark","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3082031.3083247"},{"key":"ref14","article-title":"Faceswap: Deepfakes Software","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2190402"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534089"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118423"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03867-9"},{"key":"ref23","article-title":"Mover: Mask and recovery based facial part consistency aware method for deepfake video detection","author":"Hu","year":"2023","journal-title":"arXiv preprint arXiv: 2303.01740"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3217892"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3579731.3579810"},{"key":"ref27","article-title":"Fakeavceleb: A novel audio-video multimodal deepfake dataset","author":"Khalid","year":"2021","journal-title":"Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1210384"},{"key":"ref29","article-title":"Fakeout: Leveraging out-of-domain self-supervision for multi-modal video deepfake detection","author":"Knafo","year":"2022","journal-title":"arXiv preprint arXiv:2212.00773"},{"key":"ref30","article-title":"FaceSwap: Deep Learning for Face Swapping","author":"Kowalski","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_39"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref37","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2017.8267647"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3154404"},{"key":"ref42","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"International Conference on Machine Learning","volume":"32","author":"Rezende"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892905"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref48","article-title":"Real face foundation representation learning for generalized deepfake detection","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv: 2303.08439"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00931"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_7"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20130"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3596947.3596959"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68821-9_38"},{"issue":"146","key":"ref56","first-page":"10","article-title":"Converting video formats with ffmpeg","volume":"2006","author":"Tomar","year":"2006","journal-title":"Linux Journal"},{"key":"ref57","article-title":"Deepfake video detection using convolutional vision transformer","author":"Wodajo","year":"2021","journal-title":"arXiv preprint arXiv: 2102.11126"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995566"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1080\/02564602.2014.987328"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00044"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1049\/bme2.12031"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428368"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"ref66","article-title":"Self-supervised transformer for deepfake detection","author":"Zhao","year":"2022","journal-title":"arXiv preprint arXiv:2203.01265"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_23"}],"event":{"name":"2023 IEEE International Joint Conference on Biometrics (IJCB)","location":"Ljubljana, Slovenia","start":{"date-parts":[[2023,9,25]]},"end":{"date-parts":[[2023,9,28]]}},"container-title":["2023 IEEE International Joint Conference on Biometrics (IJCB)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10447019\/10448524\/10449301.pdf?arnumber=10449301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,8]],"date-time":"2024-03-08T01:26:14Z","timestamp":1709861174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10449301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,25]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/ijcb57857.2023.10449301","relation":{},"subject":[],"published":{"date-parts":[[2023,9,25]]}}}