{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T19:58:45Z","timestamp":1781035125514,"version":"3.54.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100006465","name":"Korea Creative Content Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006465","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01046","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11241-11251","source":"Crossref","is-referenced-by-count":1,"title":["MemoryTalker: Personalized Speech-Driven 3D Facial Animation via Audio-Guided Stylization"],"prefix":"10.1109","author":[{"given":"Hyung Kyu","family":"Kim","sequence":"first","affiliation":[{"name":"Chung-Ang University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sangmin","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hak Gu","family":"Kim","sequence":"additional","affiliation":[{"name":"Chung-Ang University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1200072"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02009"},{"key":"ref3","article-title":"Personalized speech-driven expressive 3d facial animation synthesis with style control","volume-title":"arXiv preprint","author":"Bozkurt","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00429"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01619"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2006.08.017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10249"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1595"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_12"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01356"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01305"},{"key":"ref17","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27945"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647359"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00036"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.20003"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00307"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01028"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3107669"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3100087"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43412-9_12"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.10.005"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2007-11508"},{"key":"ref38","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01885"},{"issue":"11","key":"ref42","article-title":"Visualizing data using t -sne","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref43","article-title":"Memory networks","author":"Weston","year":"2014","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611775"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_14"},{"key":"ref47","first-page":"27294","article-title":"Probabilistic speech-driven 3d facial motion synthesis: new benchmarks methods and applications","volume-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Karren","year":"2024"},{"key":"ref48","article-title":"Chan. Learning Dynamic Memory Networks for Object Tracking","author":"Yang","year":"2018","journal-title":"In ECCV"},{"key":"ref49","article-title":"Audio-driven talking face video generation with learning-based personalized head pose","author":"Yi","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3113981"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657413"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00440"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3476275"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443376.pdf?arnumber=11443376","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T19:49:34Z","timestamp":1781034574000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443376\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01046","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}