{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:52:06Z","timestamp":1761396726205,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"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":[[2023,12,4]]},"DOI":"10.1109\/vcip59821.2023.10402739","type":"proceedings-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T18:35:59Z","timestamp":1706553359000},"page":"1-5","source":"Crossref","is-referenced-by-count":2,"title":["SpeechSyncNet: Speech to Talking Landmark via the fusion of prior frame landmark and the audio"],"prefix":"10.1109","author":[{"given":"Xuan-Nam","family":"Cao","sequence":"first","affiliation":[{"name":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"}]},{"given":"Quoc-Huy","family":"Trinh","sequence":"additional","affiliation":[{"name":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"}]},{"given":"Van-Son","family":"Ho","sequence":"additional","affiliation":[{"name":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"}]},{"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[{"name":"University of Science,Faculty of Information Technology,Ho Chi Minh City,Vietnam"}]}],"member":"263","reference":[{"article-title":"What comprises a good talking-head video generation?: A survey and benchmark","year":"2020","author":"Chen","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351066"},{"article-title":"Landmark assisted cyclegan for cartoon face generation","year":"2019","author":"Wu","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93764-9_35"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2020.107398"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096358"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"},{"key":"ref10","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1860"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201292"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682061"},{"article-title":"Mediapipe: A framework for building perception pipelines","year":"2019","author":"Lugaresi","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/184"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3099900"}],"event":{"name":"2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)","start":{"date-parts":[[2023,12,4]]},"location":"Jeju, Korea, Republic of","end":{"date-parts":[[2023,12,7]]}},"container-title":["2023 IEEE International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10402600\/10402106\/10402739.pdf?arnumber=10402739","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T01:06:37Z","timestamp":1710378397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10402739\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/vcip59821.2023.10402739","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]}}}