{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T17:56:05Z","timestamp":1793901365985,"version":"4.8.0"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20332,62461160331,62276247"],"award-info":[{"award-number":["U24A20332,62461160331,62276247"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00296","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3091-3100","source":"Crossref","is-referenced-by-count":2,"title":["Not Only Vision: Evolve Visual Speech Recognition via Peripheral Information"],"prefix":"10.1109","author":[{"given":"Zhaoxin","family":"Yuan","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety,Beijing,China,100190"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety,Beijing,China,100190"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety,Beijing,China,100190"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences,State Key Laboratory of AI Safety,Beijing,China,100190"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref2","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2024-432"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2015-177"},{"key":"ref5","article-title":"Lipnet: End-to-end sentence-level lipreading","author":"Assael","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref6","article-title":"Seed-asr: Understanding diverse speech and contexts with 11 m -based speech recognition","author":"Bai","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","article-title":"Large language models are strong audio-visual speech recognition learners","author":"Cappellazzo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446532"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref10","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3107946"},{"key":"ref13","article-title":"Continuous automatic speech recognition by lipreading","volume-title":"Motion-Based recognition","author":"Alan J","year":"1997"},{"key":"ref14","article-title":"Jointly learning visual and auditory speech representations from raw data","author":"Haliassos","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref15","article-title":"Unified speech recognition: A single model for auditory, visual, and audiovisual inputs","author":"Haliassos","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref16","article-title":"LoRA: LowRank Adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu","year":"2022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687898"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2986"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.21437\/AVSP.2017-13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446898"},{"key":"ref21","article-title":"Improving visual features for lip-reading","author":"Lan","year":"2010","journal-title":"Auditory-visual speech processing 2010"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01803"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1996.0570"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref29","article-title":"Enhancing large language model-based speech recognition by contextualization for rare and ambiguous words","author":"Nozawa","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587734"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096149"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/57167.57170"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-2290"},{"key":"ref35","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746126"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-10920"},{"key":"ref38","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","author":"Shazeer","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref39","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","author":"Shi","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-1669"},{"key":"ref41","first-page":"1255","article-title":"Improving domain-specific asr with 11 m -generated contextual descriptions","volume-title":"Conference of the International Speech Communication Association","author":"Suh"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907309"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0304"},{"key":"ref44","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref45","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.666"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3352388"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00080"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02556"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.108"},{"key":"ref51","article-title":"Asymmetry in low-rank adapters of foundation models","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275873"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445478.pdf?arnumber=11445478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:59Z","timestamp":1777611599000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00296","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}