{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:14:31Z","timestamp":1761894871224,"version":"build-2065373602"},"reference-count":43,"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"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209403","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":0,"title":["Enhanced Self-Supervised Multi-View Representations with Modality-Missing Robustness for Audio-Visual Speech Recognition"],"prefix":"10.1109","author":[{"given":"Fei","family":"Su","sequence":"first","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China,430072"}]},{"given":"Cancan","family":"Li","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Computer Science,Wuhan,China,430072"}]},{"given":"Juan","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University,School of Artificial Intelligence,Wuhan,China,430072"}]}],"member":"263","reference":[{"volume-title":"Automatic lipreading to enhance speech recognition (speech reading)","year":"1984","author":"Petajan","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.1998.999008"},{"article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","year":"2018","author":"Afouras","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/scj.4690220607"},{"key":"ref5","article-title":"Attention bottlenecks for multimodal fusion","volume":"34","author":"Nagrani","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5361"},{"article-title":"Learning audio-visual speech representation by masked multi-modal cluster prediction","volume-title":"Proc. ICLR","author":"Shi","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.666"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889251"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-322"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683733"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1155\/2007\/64506"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682566"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3395035.3425202"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01810"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479908"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1994.389567"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS.2016.7550888"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462964"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-99"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1669"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2018.2889052"},{"article-title":"First order motion model for image animation","volume-title":"Proc. NeurIPS","author":"Siarohin","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201283"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9004036"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298679"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2927975"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2833052"},{"issue":"6","key":"ref41","first-page":"865","article-title":"An approach to fast eye location and face plane rotation correction","volume":"25","author":"Wang","year":"2013","journal-title":"Journal of Computer-Aided Design & Computer Graphics"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163155"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8297030"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","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\/11209403.pdf?arnumber=11209403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:38:03Z","timestamp":1761889083000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209403","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}