{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:58:06Z","timestamp":1784041086731,"version":"3.55.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tmm.2021.3115626","type":"journal-article","created":{"date-parts":[[2021,10,11]],"date-time":"2021-10-11T20:38:32Z","timestamp":1633984712000},"page":"4342-4355","source":"Crossref","is-referenced-by-count":32,"title":["CroMM-VSR: Cross-Modal Memory Augmented Visual Speech Recognition"],"prefix":"10.1109","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6514-0018","authenticated-orcid":false,"given":"Minsu","family":"Kim","sequence":"first","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-1000","authenticated-orcid":false,"given":"Joanna","family":"Hong","sequence":"additional","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8467-3576","authenticated-orcid":false,"given":"Se Jin","family":"Park","sequence":"additional","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865479"},{"key":"ref2","article-title":"Audio visual speech recognition","author":"Neti","year":"2000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-014-0629-7"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2002.5745027"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.922789"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SCSP.2017.7973348"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1117\/12.689960"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6288999"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref13","first-page":"1","article-title":"Multi-grained spatio-temporal modeling for lip-reading","volume-title":"Proc. British Mach. Vis. Conf.","author":"Wang","year":"2019"},{"key":"ref14","first-page":"269","article-title":"Learning spatio-temporal features with two-stream deep 3D CNNs for lipreading","volume-title":"Proc. British Mach. Vis. Conf.","author":"Weng","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00132"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.04.010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"ref18","first-page":"1243","article-title":"Convolutional sequence to sequence learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gehring","year":"2017"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref21","article-title":"LipNet: End-to-end sentence-level lipreading","author":"Assael","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican1292-108"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref24","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00921"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3284750"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6817"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.155"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2407694"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6174"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00133"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00134"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref42","first-page":"1","article-title":"Synchronous bidirectional learning for multilingual lip reading","volume-title":"Proc. British Mach. Vis. Conf.","author":"Luo","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref44","first-page":"1607","article-title":"Born again neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Furlanello","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00088"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2975922"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054127"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref49","article-title":"Memory networks","volume-title":"ICLR","author":"Weston","year":"2015"},{"key":"ref50","first-page":"2440","article-title":"End-to-end memory networks","volume":"28","author":"Sukhbaatar","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1147"},{"key":"ref53","article-title":"Learning to remember rare events","volume-title":"ICLR","author":"Kaiser","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00429"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00595"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2763455"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1063\/1.4902458"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00010"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413623"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"ref64","article-title":"LRS3-TED: A large-scale dataset for visual speech recognition","author":"Triantafyllos","year":"2018"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00304"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00036"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9687854\/09566778.pdf?arnumber=9566778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:19:25Z","timestamp":1705015165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9566778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tmm.2021.3115626","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}