{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T18:23:41Z","timestamp":1779906221674,"version":"3.53.1"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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":["62272143"],"award-info":[{"award-number":["62272143"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"University Synergy Innovation Program of Anhui Province","award":["GXXT-2022-054"],"award-info":[{"award-number":["GXXT-2022-054"]}]},{"name":"Anhui Provincial Major Science and Technology Project","award":["202203a05020025"],"award-info":[{"award-number":["202203a05020025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3282224","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T19:59:11Z","timestamp":1685735951000},"page":"4507-4517","source":"Crossref","is-referenced-by-count":34,"title":["LipFormer: Learning to Lipread Unseen Speakers Based on Visual-Landmark Transformers"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4962-9734","authenticated-orcid":false,"given":"Feng","family":"Xue","sequence":"first","affiliation":[{"name":"School of Software, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4654-2089","authenticated-orcid":false,"given":"Yu","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deyin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Anhui University, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7133-8311","authenticated-orcid":false,"given":"Yincen","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6119-058X","authenticated-orcid":false,"given":"Lin","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6174"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019211"},{"key":"ref3","first-page":"86","article-title":"Comparison of human and machine-based lip-reading","volume-title":"Proc. AVSP","author":"Hilder"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-739X(03)00145-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3065578"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00133"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3366579"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00088"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/app11156975"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132068"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413740"},{"key":"ref15","article-title":"LipNet: End-to-end sentence-level lipreading","author":"Assael","year":"2016","journal-title":"arXiv:1611.01599"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.6"},{"key":"ref17","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref18","first-page":"369","article-title":"Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Auvolat"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475420"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00285"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MVIP53647.2022.9738754"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2172427"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130393"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1121\/1.403994"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2001.962703"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1006\/cviu.1996.0570"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462280"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-421"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461900"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref34","first-page":"143","article-title":"Automatic lipreading with principle component analysis","volume-title":"Proc. 2nd Int. Conf.","author":"Yavuz"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3524620"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1107"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/DSC50466.2020.00020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00550-z"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2871262"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2891244"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979190"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548195"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3240195"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10143326.pdf?arnumber=10143326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T08:56:51Z","timestamp":1709283411000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10143326\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":45,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3282224","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}