{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T10:55:09Z","timestamp":1782298509021,"version":"3.54.5"},"reference-count":72,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,3]],"date-time":"2024-01-03T00:00:00Z","timestamp":1704240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,3]]},"DOI":"10.1109\/wacv57701.2024.00412","type":"proceedings-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T17:36:09Z","timestamp":1712684169000},"page":"4156-4166","source":"Crossref","is-referenced-by-count":5,"title":["RADIO: Reference-Agnostic Dubbing Video Synthesis"],"prefix":"10.1109","author":[{"given":"Dongyeun","family":"Lee","sequence":"first","affiliation":[{"name":"Klleon AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaewon","family":"Kim","sequence":"additional","affiliation":[{"name":"Klleon AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sangjoon","family":"Yu","sequence":"additional","affiliation":[{"name":"Klleon AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaejun","family":"Yoo","sequence":"additional","affiliation":[{"name":"UNIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gyeong-Moon","family":"Park","sequence":"additional","affiliation":[{"name":"Kyung Hee University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2889052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548101"},{"key":"ref3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-11"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-1064"},{"key":"ref9","article-title":"You said that?","volume-title":"British Machine Vision Conference (BMVC)","author":"Chung"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"ref12","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"ICLR","author":"Dosovitskiy"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01413"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref17","article-title":"Lip reading in the wild","volume-title":"Asian Conference on Computer Vision (ACCV)","author":"Zisserman"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01778"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351066"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00278"},{"key":"ref28","article-title":"Vitgan: Training gans with vision transformers","author":"Lee","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref37","author":"Min","year":"2022","journal-title":"Styletalker: One-shot style-based audio-driven talking head video generation"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00290"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref45","author":"Tang","year":"2022","journal-title":"Memories are one-to-many mapping alleviators in talking face generation"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00077"},{"key":"ref49","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"International conference on machine learning","author":"Touvron"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.3023573"},{"key":"ref56","first-page":"12077","article-title":"Segformer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref57","article-title":"Dfanerf: Personalized talking head generation via disentangled face attributes neural rendering","author":"Yao","year":"2022"},{"key":"ref58","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01102"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref66","first-page":"18367","article-title":"Improved transformer for high-resolution gans","volume":"34","author":"Zhao","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"issue":"6","key":"ref71","first-page":"1","article-title":"Makeittalk: speaker-aware talking-head animation","volume":"39","author":"Zhou","year":"2020","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"}],"event":{"name":"2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Waikoloa, HI, USA","start":{"date-parts":[[2024,1,3]]},"end":{"date-parts":[[2024,1,8]]}},"container-title":["2024 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10483279\/10483282\/10484196.pdf?arnumber=10484196","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T05:54:37Z","timestamp":1712728477000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10484196\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,3]]},"references-count":72,"URL":"https:\/\/doi.org\/10.1109\/wacv57701.2024.00412","relation":{},"subject":[],"published":{"date-parts":[[2024,1,3]]}}}