{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T06:07:07Z","timestamp":1759385227032,"version":"3.37.3"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,19]],"date-time":"2021-09-19T00:00:00Z","timestamp":1632009600000},"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":[[2021,9,19]]},"DOI":"10.1109\/icip42928.2021.9506396","type":"proceedings-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T21:08:41Z","timestamp":1629752921000},"page":"2493-2497","source":"Crossref","is-referenced-by-count":9,"title":["Speaker-Independent Lipreading By Disentangled Representation Learning"],"prefix":"10.1109","author":[{"given":"Qun","family":"Zhang","sequence":"first","affiliation":[{"name":"Shanghai Jiaotong University,School of Electronic Information and Electrical Engineering,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shilin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiaotong University,School of Electronic Information and Electrical Engineering,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gongliang","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiaotong University,School of Electronic Information and Electrical Engineering,Shanghai,China,200240"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1609\/aaai.v33i01.33012588"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/ICIP40778.2020.9190780"},{"key":"ref13","article-title":"Deep audio-visual speech recognition","author":"afouras","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis & Machine Intelligence"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/CVPR42600.2020.01332"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/CVPR42600.2020.00518"},{"key":"ref16","first-page":"517","article-title":"Learning to decompose and disentangle representations for video prediction","author":"hsieh","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1145\/3123266.3123451"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/CVPR.2018.00795"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1007\/978-3-030-36808-1_18"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1016\/j.imavis.2018.07.002"},{"key":"ref3","article-title":"Lipnet: end-to-end sentence-level lip-reading","author":"assael","year":"2016","journal-title":"arXiv 1611 01599v2"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/ICCV.2019.00080"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1007\/s10489-014-0629-7"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1121\/1.2229005"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICASSP.2016.7472088"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICIP40778.2020.9190976"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref9","first-page":"3662","article-title":"Improving speaker-independent lip-reading with domain-adversarial training","author":"wand","year":"2015","journal-title":"Proceedings of Interspeech"},{"key":"ref20","first-page":"87","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conference on Computer Vision"}],"event":{"name":"2021 IEEE International Conference on Image Processing (ICIP)","start":{"date-parts":[[2021,9,19]]},"location":"Anchorage, AK, USA","end":{"date-parts":[[2021,9,22]]}},"container-title":["2021 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9506008\/9506009\/09506396.pdf?arnumber=9506396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T23:57:19Z","timestamp":1670371039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9506396\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,19]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icip42928.2021.9506396","relation":{},"subject":[],"published":{"date-parts":[[2021,9,19]]}}}