{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T11:41:40Z","timestamp":1783597300198,"version":"3.55.0"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/icpr56361.2022.9956316","type":"proceedings-article","created":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T19:34:13Z","timestamp":1669750453000},"page":"274-280","source":"Crossref","is-referenced-by-count":6,"title":["Audio-Driven Deformation Flow for Effective Lip Reading"],"prefix":"10.1109","author":[{"given":"Dalu","family":"Feng","sequence":"first","affiliation":[{"name":"Institute of Computing Technology,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiguang","family":"Shan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xilin","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology,Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS),Beijing,China,100190"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Multi-grained spatio-temporal modeling for lip-reading","author":"wang","year":"2019","journal-title":"The 30th British Machine Vision Conference(2019)"},{"key":"ref32","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Sub-word level lip reading with visual attention","author":"afouras","year":"2021"},{"key":"ref30","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00134"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00010"},{"key":"ref34","article-title":"Learning spatio-temporal features with twostream deep 3d cnns for lipreading","author":"weng","year":"2019","journal-title":"The 30th British Machine Vision Conference(2019)"},{"key":"ref10","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2018.10.003"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3338533.3366579"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2015.7163155"},{"key":"ref15","article-title":"Towards practical lipreading with distilled and efficient models","author":"ma","year":"2020","journal-title":"ICASSP 2020-2020 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP)"},{"key":"ref16","article-title":"Distilling the knowledge in a neural network","author":"hinton","year":"2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682775"},{"key":"ref19","first-page":"251","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00133"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-85"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639643"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756582"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00132"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054253"},{"key":"ref2","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6174"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1943"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682524"},{"key":"ref22","first-page":"4176","article-title":"Posecontrollable talking face generation by implicitly modularized audiovisual representation","author":"zhou","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref23","article-title":"Arbitrary talking face generation via attentional audio-visual coherence learning","author":"zhu","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"}],"event":{"name":"2022 26th International Conference on Pattern Recognition (ICPR)","location":"Montreal, QC, Canada","start":{"date-parts":[[2022,8,21]]},"end":{"date-parts":[[2022,8,25]]}},"container-title":["2022 26th International Conference on Pattern Recognition (ICPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9956007\/9955631\/09956316.pdf?arnumber=9956316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T20:06:00Z","timestamp":1671480360000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956316\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icpr56361.2022.9956316","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}