{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:43:31Z","timestamp":1760147011289,"version":"build-2065373602"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100016011","name":"Saint Francis University","doi-asserted-by":"publisher","award":["ISG200206"],"award-info":[{"award-number":["ISG200206"]}],"id":[{"id":"10.13039\/100016011","id-type":"DOI","asserted-by":"publisher"}]},{"name":"UGC, Hong Kong, SAR","award":["UGC\/IDS(C)11\/E01\/20"],"award-info":[{"award-number":["UGC\/IDS(C)11\/E01\/20"]}]},{"DOI":"10.13039\/501100004377","name":"Hong Kong Polytechnic University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Consumer Electron."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tce.2024.3516387","type":"journal-article","created":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T17:32:33Z","timestamp":1733938353000},"page":"379-387","source":"Crossref","is-referenced-by-count":0,"title":["Photo-Realistic Talking Face Generation Under Latent Space Manipulation"],"prefix":"10.1109","volume":"71","author":[{"given":"Ridwan","family":"Salahudeen","sequence":"first","affiliation":[{"name":"School of Computing and Information Sciences, Saint Francis University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8280-0367","authenticated-orcid":false,"given":"Wan-Chi","family":"Siu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronics Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7479-0787","authenticated-orcid":false,"given":"H.","family":"Anthony Chan","sequence":"additional","affiliation":[{"name":"School of Computing and Information Sciences, Saint Francis University, Hong Kong, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/jcmc\/zmz026"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2022.3206114"},{"volume-title":"Latency vs bandwidth: Unraveling video conferencing quality secrets.","year":"2023","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.2970919"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01150-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr42600.2020.00926"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00453"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459838"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00416"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/152"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref15","first-page":"1","article-title":"First order motion model for image animation","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","author":"Siarohin"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/wacv45572.2020.9093474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01344"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00339"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00991"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2019.2899869"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2023.3236972"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-0855-0_42"},{"key":"ref23","first-page":"1","article-title":"Learning audio-visual speech representation by masked multimodal cluster prediction","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Shi"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_11"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01796"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01408"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00938"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/icce-taiwan58799.2023.10227004"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1117\/12.2668398"}],"container-title":["IEEE Transactions on Consumer Electronics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/30\/11038962\/10794696.pdf?arnumber=10794696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T17:36:44Z","timestamp":1760117804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10794696\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":30,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tce.2024.3516387","relation":{},"ISSN":["0098-3063","1558-4127"],"issn-type":[{"type":"print","value":"0098-3063"},{"type":"electronic","value":"1558-4127"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}