{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:58:07Z","timestamp":1784041087270,"version":"3.55.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"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":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094693","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":12,"title":["Multi-Temporal Lip-Audio Memory for Visual Speech Recognition"],"prefix":"10.1109","author":[{"given":"Jeong Hun","family":"Yeo","sequence":"first","affiliation":[{"name":"KAIST,School of Electrical Engineering,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minsu","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST,School of Electrical Engineering,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"KAIST,School of Electrical Engineering,South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"2857","article-title":"Lip-reading with densely connected temporal convolutional networks","author":"ma","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision"},{"key":"ref12","first-page":"1","article-title":"Lrw-1000: A naturally-distributed large-scale benchmark for lip reading in the wild","author":"yang","year":"2019","journal-title":"2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00010"},{"key":"ref14","author":"wang","year":"2019","journal-title":"Multi-grained spatio-temporal modeling for lip-reading"},{"key":"ref11","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746706"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00510"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414567"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00132"},{"key":"ref16","author":"weng","year":"2019","journal-title":"Learning spatio-temporal features with two-stream deep 3d cnns for lipreading"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01444"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00133"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747052"},{"key":"ref23","author":"ma","year":"2021","journal-title":"Lira Learning visual speech representations from audio through self-supervision"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556628"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00134"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415063"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053841"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"ref7","article-title":"Cromm-vsr: Cross-modal memory augmented visual speech recognition","author":"kim","year":"2021","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.113"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/scientificamerican1292-108"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_33"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01312"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6174"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094693.pdf?arnumber=10094693","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:06:55Z","timestamp":1700507215000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094693\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094693","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}