{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:33:26Z","timestamp":1774539206711,"version":"3.50.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,15]],"date-time":"2021-12-15T00:00:00Z","timestamp":1639526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,15]]},"DOI":"10.1109\/fg52635.2021.9667026","type":"proceedings-article","created":{"date-parts":[[2022,1,26]],"date-time":"2022-01-26T05:34:23Z","timestamp":1643175263000},"page":"1-7","source":"Crossref","is-referenced-by-count":16,"title":["Demystifying Attention Mechanisms for Deepfake Detection"],"prefix":"10.1109","author":[{"given":"Abhijit","family":"Das","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Srijan","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Antitza","family":"Dantcheva","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"2638","DOI":"10.1609\/aaai.v35i3.16367","article-title":"Domain general face forgery detection by learning to weight","volume":"35","author":"sun","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref38","article-title":"How to train your vit? data, augmentation, and regularization in vision transformers","author":"steiner","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1109\/WIFS.2017.8267647","article-title":"Distinguishing computer graphics from natural images using convolution neural networks","author":"rahmouni","year":"2017","journal-title":"Information Forensics and Security (WIFS) 2017 IEEE International Workshop"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00008"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.05.003"},{"key":"ref30","article-title":"In ictu oculi: Exposing AI generated fake face videos by detecting eye blinking","author":"li","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref37","article-title":"The upside of deep fakes","volume":"78","author":"silbey","year":"2018","journal-title":"Md L Rev"},{"key":"ref36","article-title":"Recurrent convolutional strategies for face manipulation detection in videos","volume":"3","author":"sabir","year":"2019","journal-title":"Interfaces (GUI)"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-87664-7_10","article-title":"Comparing 3D CNN architectures and attention mechanisms for deepfake detection","author":"roy","year":"2022","journal-title":"Handbook of Digital Face Manipulation and Detection"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553270"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1145\/3197517.3201283","article-title":"Deep video portraits","volume":"37","author":"kim","year":"2018","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICB45273.2019.8987375"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS49906.2020.9360904"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref21","article-title":"Deepfakeson-phys: Deepfakes detection based on heart rate estimation","author":"hernandez-ortega","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00296"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00336"},{"key":"ref25","volume":"abs 1705 6950","author":"kay","year":"2017","journal-title":"The kinetics human action video dataset"},{"key":"ref50","article-title":"InMoDeGAN interpretable motion decomposition generative adversarial network for video generation","author":"wang","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref51","article-title":"A video is worth more than 1000 lies. comparing 3dcnn approaches for detecting deepfakes","author":"wang","year":"2020","journal-title":"FG'20 15th IEEE International Conference on Automatic Face and Gesture Recognition"},{"key":"ref53","article-title":"Adversarial attacks and defenses in images, graphs and text: A review","author":"xu","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.23919\/BIOSIG.2018.8553377"},{"key":"ref10","first-page":"2018","article-title":"Deep fakes: A looming challenge for privacy, democracy, and national security. 107 california law review (2019, forthcoming); U of Texas Law","author":"chesney","year":"2018","journal-title":"Public Law Research Paper"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1145\/3072959.3073640","article-title":"Synthesizing obama: learning lip sync from audio","volume":"36","author":"suwajanakorn","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3082031.3083247"},{"key":"ref13","article-title":"ID-Reveal: Identity-aware deepfake video detection","author":"cozzolino","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00582"},{"key":"ref15","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"ICLRE"},{"key":"ref16","first-page":"1","article-title":"Don't believe it if you see it: Deep fakes and distrust","author":"eichensehr","year":"2018","journal-title":"Jotwell J Things We Like"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2012.2190402"},{"key":"ref18","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00341"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00152"},{"key":"ref3","first-page":"38","article-title":"Protecting world leaders against deep fakes","author":"agarwal","year":"2019","journal-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2909827.2930786"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1145\/3130800.3130818","article-title":"Bringing portraits to life","volume":"36","author":"averbuch-elor","year":"2017","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref7","volume":"abs 2102 5095","author":"bertasius","year":"2021","journal-title":"Is space-time attention all you need for video understanding?"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00202"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00531"},{"key":"ref47","article-title":"G3AN: This video does not exist. Disentangling motion and appearance for video generation","author":"wang","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"ref41","article-title":"Deferred neural rendering: Image synthesis using neural textures","author":"thies","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref44","article-title":"Mlp-mixer: An all-mlp architecture for vision","author":"tolstikhin","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref43","article-title":"Deepfakes evolution: Analysis of facial regions and fake detection performance","author":"tolosana","year":"2020","journal-title":"ArXiv Preprint"}],"event":{"name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","location":"Jodhpur, India","start":{"date-parts":[[2021,12,15]]},"end":{"date-parts":[[2021,12,18]]}},"container-title":["2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9666787\/9666788\/09667026.pdf?arnumber=9667026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,24]],"date-time":"2023-01-24T20:00:21Z","timestamp":1674590421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9667026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,15]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/fg52635.2021.9667026","relation":{},"subject":[],"published":{"date-parts":[[2021,12,15]]}}}