{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:30:34Z","timestamp":1761895834976,"version":"build-2065373602"},"reference-count":24,"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\/icme59968.2025.11209943","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":["Chinese-LiPS: A Chinese Audio-Visual Speech Recognition Dataset with Lip-Reading and Presentation Slides"],"prefix":"10.1109","author":[{"given":"Jinghua","family":"Zhao","sequence":"first","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Jia","sequence":"additional","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyao","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaming","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Qin","sequence":"additional","affiliation":[{"name":"Nankai University,College of Computer Science,Tianjin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-322"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445941"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2032"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-776"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.alvr-1.11"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448079"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-488"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448106"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"issue":"5","key":"ref14","first-page":"3878","article-title":"Lrs3-ted: a large-scale dataset for visual speech recognition","volume":"123","author":"Afouras","year":"2008","journal-title":"corpus"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3366579"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1674"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095796"},{"article-title":"How2: A large-scale dataset for multimodal language understanding","volume-title":"NeurIPS","author":"Sanabria","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446142"},{"article-title":"Multi-modal speech transformer decoders: When do multiple modalities improve accuracy?","year":"2024","author":"Guan","key":"ref21"},{"article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"International Conference on Learning Representations","author":"Shi","key":"ref22"},{"key":"ref23","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"International conference on machine learning","author":"Radford"},{"article-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","year":"2024","author":"Wang","key":"ref24"}],"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\/11209943.pdf?arnumber=11209943","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T06:00:02Z","timestamp":1761890402000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209943\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209943","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}