{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T23:13:27Z","timestamp":1773962007913,"version":"3.50.1"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100008858","name":"Taihu Lake Innovation Fund for Future Technology, Huazhong University of Science and Technology","doi-asserted-by":"publisher","award":["2023-B-8"],"award-info":[{"award-number":["2023-B-8"]}],"id":[{"id":"10.13039\/501100008858","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities, HUST","doi-asserted-by":"publisher","award":["82400049"],"award-info":[{"award-number":["82400049"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271221"],"award-info":[{"award-number":["62271221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2025.3539220","type":"journal-article","created":{"date-parts":[[2025,2,5]],"date-time":"2025-02-05T14:22:17Z","timestamp":1738765337000},"page":"11794-11807","source":"Crossref","is-referenced-by-count":1,"title":["Toward Micro Lip Reading in the Wild: Dataset, Theory, and Practices"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4340-0018","authenticated-orcid":false,"given":"Ran","family":"Wang","sequence":"first","affiliation":[{"name":"School of Journalism and Information Communication and the School of Future Technology, Huazhong University of Science and Technology, Wuhan, China"}]},{"given":"Yingsong","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Electronic Information, Wuhan University, Wuhan, China"}]},{"given":"Anqi","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4635-1231","authenticated-orcid":false,"given":"Shengtao","family":"Zhong","sequence":"additional","affiliation":[{"name":"School of Journalism and Information Communication, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8968-8507","authenticated-orcid":false,"given":"Xiang","family":"Liao","sequence":"additional","affiliation":[{"name":"Donald Bren School of Information and Computer Sciences, University of California, Irvine, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9951-5420","authenticated-orcid":false,"given":"Yanjiu","family":"He","sequence":"additional","affiliation":[{"name":"School of Software and Microelectronics, Peking University, Beijing, China"}]},{"given":"Han","family":"Ye","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"given":"Chutian","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Mechanical Science and Engineering, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3089-0536","authenticated-orcid":false,"given":"Qinlao","family":"Zhao","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7805-4959","authenticated-orcid":false,"given":"Min","family":"Du","sequence":"additional","affiliation":[{"name":"ByteDance, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7739-4146","authenticated-orcid":false,"given":"Yang","family":"Xiao","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref2","article-title":"Deep audio-visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv:1809.02108"},{"key":"ref3","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Afouras","year":"2018","journal-title":"arXiv:1809.00496"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2009.2030637"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163155"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-293"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2010.5641954"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2015.7340989"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref13","article-title":"LipNet: End-to-end sentence-level lipreading","author":"Assael","year":"2016","journal-title":"arXiv:1611.01599"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00134"},{"key":"ref15","first-page":"69","article-title":"Patch-based analysis of visual speech from multiple views","volume-title":"Proc. Int. Conf. Auditory-Vis. Speech Process.","author":"Lucey"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2012.116"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00088"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.004"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.817150"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref21","article-title":"Learn an effective lip reading model without pains","author":"Feng","year":"2020","journal-title":"arXiv:2011.07557"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00290"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2007.4379312"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995345"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760575"},{"key":"ref26","first-page":"1","article-title":"Audio-visual automatic speech recognition: An overview","volume":"22","author":"Potamianos","year":"2004","journal-title":"Issues Vis. Audio Vis. Speech Process."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865702206162"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1155\/S1110865702206083"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1996.0570"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2001.1237849"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.2011515"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472029"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2018.07.002"},{"key":"ref34","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"25","author":"Krizhevsky"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472852"},{"key":"ref37","first-page":"251","article-title":"Out of time: Automated lip sync in the wild","volume-title":"Proc. Asian Conf. Comput. Vis.","author":"Chung"},{"key":"ref38","article-title":"Lip reading using CNN and LSTM","author":"Garg","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref40","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref41","first-page":"1","article-title":"Improving visual features for lip-reading","volume-title":"Proc. Pro. Int. Conf. Auditory-Visual Speech Process.","author":"Lan"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2012.2229986"},{"key":"ref44","first-page":"27503","article-title":"Efficiently identifying task groupings for multi-task learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Fifty"},{"key":"ref45","article-title":"RTMPose: Real-time multi-person pose estimation based on MMPose","author":"Jiang","year":"2023","journal-title":"arXiv:2303.07399"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096889"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2008-537"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10876180.pdf?arnumber=10876180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T20:10:12Z","timestamp":1773951012000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10876180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3539220","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}