{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T14:42:24Z","timestamp":1783608144828,"version":"3.55.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"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":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747729","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"8467-8471","source":"Crossref","is-referenced-by-count":34,"title":["Accurate and Resource-Efficient Lipreading with Efficientnetv2 and Transformers"],"prefix":"10.1109","author":[{"given":"Alexandros","family":"Koumparoulis","sequence":"first","affiliation":[{"name":"University of Thessaly,Electrical and Computer Engineering Department,Volos,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerasimos","family":"Potamianos","sequence":"additional","affiliation":[{"name":"University of Thessaly,Electrical and Computer Engineering Department,Volos,Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1360"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3146"},{"key":"ref33","article-title":"Language modeling with gated convolutional networks","author":"dauphin","year":"2017","journal-title":"Proc ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63820-7_63"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref35","article-title":"Deep networks with stochastic depth","author":"huang","year":"2016","journal-title":"Proc ECCV"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.218"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref11","article-title":"LipNet: End-to-end sentence-level lipreading","author":"assael","year":"2016","journal-title":"CoRR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging7050091"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.21437\/Interspeech.2017-85","article-title":"Combining residual networks with LSTMs for lipreading","author":"stafylakis","year":"2017","journal-title":"Proc INTERSPEECH"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.cviu.2018.10.003","article-title":"Pushing the boundaries of audiovisual word recognition using residual networks and LSTMs","volume":"176 177","author":"stafylakis","year":"2018","journal-title":"Comp Vision Image Understand"},{"key":"ref14","article-title":"Multi-grained spatio-temporal modeling for lipreading","author":"wang","year":"2019","journal-title":"Proc BMVC"},{"key":"ref15","article-title":"Learning spatio-temporal features with two-stream deep 3D CNNs for lipreading","author":"weng","year":"2019","journal-title":"Proc BMVC"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00010"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00080"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00132"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00133"},{"key":"ref28","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461326"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2618"},{"key":"ref6","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Proc ACCV"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref8","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc ICML"},{"key":"ref7","article-title":"Lipreading with densely connected temporal convolutional networks","author":"ma","year":"2021","journal-title":"Proc WACV"},{"key":"ref2","article-title":"MobiVSR: A visual speech recognition solution for mobile devices","author":"shrivastava","year":"2019","journal-title":"CoRR"},{"key":"ref9","article-title":"EfficientNetV2: Smaller models and faster training","author":"tan","year":"2021","journal-title":"Proc ICML"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref20","article-title":"Can we read speech beyond the lips? Rethinking RoI selection for deep visual speech recognition","author":"zhang","year":"2020","journal-title":"Proc FG"},{"key":"ref22","article-title":"Learn an effective lip reading model without pains","author":"feng","year":"2020","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref24","article-title":"Synchronous bidirectional learning for multilingual lip reading","author":"luo","year":"2020","journal-title":"Proc BMVC"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-723"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414659"},{"key":"ref26","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NeurIPS"},{"key":"ref25","article-title":"Spatio-temporal attention mechanism and knowledge distillation for lip reading","author":"elashmawy","year":"2021","journal-title":"CoRR"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747729.pdf?arnumber=9747729","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:05:37Z","timestamp":1660579537000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747729\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747729","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}