{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:03:55Z","timestamp":1780761835762,"version":"3.54.1"},"reference-count":70,"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\/100024171","name":"Bavarian Research Institute for Digital Transformation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100024171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","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\/iccv51701.2025.01214","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13065-13075","source":"Crossref","is-referenced-by-count":2,"title":["GaussianSpeech: Audio-Driven Personalized 3D Gaussian Avatars"],"prefix":"10.1109","author":[{"given":"Shivangi","family":"Aneja","sequence":"first","affiliation":[{"name":"Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Artem","family":"Sevastopolsky","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Kirschstein","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Justus","family":"Thies","sequence":"additional","affiliation":[{"name":"MPI-IS,Tübingen,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angela","family":"Dai","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[{"name":"Technical University of Munich,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02009"},{"key":"ref2","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00441"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00802"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681627"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.12987\/9780300280289-018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618183"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_25"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_43"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01413"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.6028\/nist.ir.4930"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00518"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01912"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72998-0_4"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351066"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3592455"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"ref30","first-page":"127","article-title":"Talkinggaussian: Structure-persistent 3d talking head synthesis via gaussian splatting","volume-title":"Computer Vision - ECCV 2024","author":"Li","year":"2025"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00521"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00070"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01919"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"ref41","volume-title":"Wrinkle Detection Streamlit","author":"Satpati","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3308441"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tifs.2022.3146783"},{"key":"ref46","volume-title":"Diffused Heads: Diffusion Models Beat GANs on Talking-Face Generation","author":"Stypu\u0142kowski","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"ref48","article-title":"Memories are one-tomany mapping alleviators in talking face generation","author":"Tang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02481-9"},{"key":"ref50","volume-title":"3diface: Diffusion-based speechdriven 3d facial animation and editing","author":"Thambiraja","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref54","volume-title":"Attention is all you need","author":"Vaswani","year":"2023"},{"key":"ref55","volume-title":"End-to-end speech-driven facial animation with temporal gans","author":"Vougioukas","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01330"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20154"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref61","article-title":"Multiface: A dataset for neural face rendering","author":"Wuu","year":"2022","journal-title":"arXiv"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref64","volume-title":"Vasa-1: Lifelike audio-driven talking faces generated in real time","author":"Xu","year":"2024"},{"key":"ref65","article-title":"Dfa-nerf: Personalized talking head generation via disentangled face attributes neural rendering","author":"Yao","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref66","article-title":"Geneface: Generalized and highfidelity audio-driven 3d talking face synthesis","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00498"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417774"}],"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\/11444594.pdf?arnumber=11444594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:42:11Z","timestamp":1777531331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444594\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01214","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}