{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T07:15:04Z","timestamp":1780384504118,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209535","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["UniSync: A Unified Framework for Audio-Visual Synchronization"],"prefix":"10.1109","author":[{"given":"Tao","family":"Feng","sequence":"first","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Xie","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Guan","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiyuan","family":"Song","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhou","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Ma","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Yu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ),Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Relative timing of sound and vision for broadcasting"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.4324\/9780080470450-13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CISP-BMEI53629.2021.9624360"},{"key":"ref4","article-title":"Geneface: Generalized and high-fidelity audio-driven 3d talking face synthesis","author":"Ye","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681108"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref9","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume":"33","author":"Kalantidis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10095796"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.07.001"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/vis.4340020404"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745053"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.02.005"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-194"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2503385.2503473"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311537"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SII.2015.7404961"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383616"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10861"},{"key":"ref23","article-title":"What comprises a good talking-head video generation?: A survey and benchmark","author":"Chen","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214100"},{"key":"ref26","article-title":"Dreamtalk: When expressive talking head generation meets diffusion probabilistic models","author":"Ma","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32946"},{"key":"ref28","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref29","article-title":"Audio-visual synchronisation in the wild","author":"Chen","year":"2021"},{"key":"ref30","article-title":"Cooperative learning of audio and video models from self-supervised synchronization","volume":"31","author":"Korbar","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref31","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351066"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209535.pdf?arnumber=11209535","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:48:49Z","timestamp":1761889729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209535\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209535","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}