{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:10:24Z","timestamp":1779379824917,"version":"3.53.1"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T00:00:00Z","timestamp":1726358400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T00:00:00Z","timestamp":1726358400000},"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":[[2024,9,15]]},"DOI":"10.1109\/ijcb62174.2024.10744480","type":"proceedings-article","created":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T18:38:05Z","timestamp":1731350285000},"page":"1-11","source":"Crossref","is-referenced-by-count":13,"title":["Contextual Cross-Modal Attention for Audio-Visual Deepfake Detection and Localization"],"prefix":"10.1109","author":[{"given":"Vinaya Sree","family":"Katamneni","sequence":"first","affiliation":[{"name":"University of North Texas at Denton,Denton,Texas,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajita","family":"Rattani","sequence":"additional","affiliation":[{"name":"University of North Texas at Denton,Denton,Texas,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS49906.2020.9360904"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00338"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00469"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-023-01248-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5220\/0010832700003124"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.593"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680795"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103818"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA56598.2022.10034605"},{"key":"ref11","author":"Chen","year":"2023","journal-title":"Npvforensics: Jointing non-critical phonemes and visemes for deepfake detection"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3625231"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2999185"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413700"},{"key":"ref16","author":"Citron","journal-title":"How deepfakes undermine truth and threaten democracy"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00101"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2023.0140144"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.392"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3231480"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.51593\/20190030"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124"},{"key":"ref26","article-title":"Demographic fairness and accountability of audio and video-based unimodal and bi-modal deepfake detectors","volume-title":"Face Recognition Across the Imaging Spectrum (FRAIS)","author":"Katamneni","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3476099.3484315"},{"key":"ref28","author":"Khalid","year":"2021","journal-title":"Fakeavceleb: A novel audio-video multimodal deepfake dataset"},{"key":"ref29","author":"Khalid","year":"2021","journal-title":"Fakeavceleb: A novel audio-video multimodal deepfake dataset"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/AIPR50011.2020.9425167"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"ref32","article-title":"Exposing deepfake videos by detecting face warping artifacts","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref34","first-page":"117010","article-title":"Magnifying multimodal forgery clues for deepfake detection","volume":"118","author":"Liu","year":"2023","journal-title":"Signal Processing: Image Communication"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3312738"},{"key":"ref36","article-title":"Attention-based multimodal learning framework for generalized audio-visual deepfake detection","author":"Masood","year":"2023","journal-title":"PREPRINT Research Square : rs.3.rs-3415144\/v1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413570"},{"key":"ref38","author":"Muda","year":"2010","journal-title":"Voice recognition algorithms using mel frequency cepstral coefficient (mfcc) and dynamic time warping (dtw) techniques"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-37742-6_25"},{"key":"ref40","article-title":"Proactive deepfake detection using gan-based visible watermarking","author":"Nadimpalli","year":"2023","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"ref41","volume-title":"Siamese Network-based Multi-modal Deepfake Detection","author":"Nekadi","year":"2020"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103525"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00728"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02559"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS55849.2022.9975428"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3057230"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00106"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3276480"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367749"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA58977.2023.00207"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00097"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095247"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095247"},{"key":"ref56","author":"Tian","year":"2023","journal-title":"Unsupervised multimodal deepfake detection using intra-and cross-modal inconsistencies"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.014"},{"key":"ref58","author":"Wang","year":"2022","journal-title":"An audio-visual attention based multimodal network for fake talking face videos detection"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3309899"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_29"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613767"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-021-11733-y"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICITES53477.2021.9637096"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08271-z"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01453"}],"event":{"name":"2024 IEEE International Joint Conference on Biometrics (IJCB)","location":"Buffalo, NY, USA","start":{"date-parts":[[2024,9,15]]},"end":{"date-parts":[[2024,9,18]]}},"container-title":["2024 IEEE International Joint Conference on Biometrics (IJCB)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10744408\/10744424\/10744480.pdf?arnumber=10744480","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T07:13:32Z","timestamp":1732691612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10744480\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,15]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/ijcb62174.2024.10744480","relation":{},"subject":[],"published":{"date-parts":[[2024,9,15]]}}}