{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T02:50:59Z","timestamp":1767840659345,"version":"3.49.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100015803","name":"Tencent","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100015803","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.02026","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T20:55:59Z","timestamp":1705352159000},"page":"22111-22120","source":"Crossref","is-referenced-by-count":10,"title":["Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video"],"prefix":"10.1109","author":[{"given":"Xiuzhe","family":"Wu","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}]},{"given":"Pengfei","family":"Hu","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Yang","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}]},{"given":"Xiaoyang","family":"Lyu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}]},{"given":"Yan-Pei","family":"Cao","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"Tencent PCG,ARC Lab"}]},{"given":"Wenming","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Zhongqian","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent AI Lab"}]},{"given":"Xiaojuan","family":"Qi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/311535.311556"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref4","article-title":"What comprises a good talking-head video generation?","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"Chen"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00852"},{"key":"ref9","article-title":"You said that?","author":"Chung","year":"2017"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref13","article-title":"Lip reading in profile","volume-title":"British Machine Vision conference","author":"Chung"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_25"},{"key":"ref15","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref17","article-title":"Obamanet: Photo-realistic\u00b4 lip-sync from text","author":"Kumar","year":"2017"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref21","article-title":"An improved noreference sharpness metric based on the probability of blur detection","volume-title":"Workshop on Video Processing and Quality Metrics","author":"Narvekar"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/QOMEX.2009.5246972"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2131660"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00554"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.09661"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref34","article-title":"Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction","author":"Wang","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref39","article-title":"Dfa-nerf: Personalized talking head generation via disentangled face attributes neural rendering","author":"Yao","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Paris, France","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10378187.pdf?arnumber=10378187","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T01:59:37Z","timestamp":1705543177000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10378187\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.02026","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}