{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T08:25:18Z","timestamp":1772007918962,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"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":[[2025,12,1]]},"DOI":"10.1109\/vcip67698.2025.11396896","type":"proceedings-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:55:27Z","timestamp":1771966527000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Transparent System For Lightweight Neural Talking Faces"],"prefix":"10.1109","author":[{"given":"Oskar","family":"Bartosz","sequence":"first","affiliation":[{"name":"Polish Academy of Sciences,Samsung R&D Institute Poland & Institute of Fundamental Technological Research,Warsaw,Poland,02-105"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"\u0141ukasz","family":"Daba\u0142a","sequence":"additional","affiliation":[{"name":"Warsaw University Of Technology,Warsaw,Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Janusz","family":"Bedkowski","sequence":"additional","affiliation":[{"name":"Polish Academy of Sciences,Samsung R&D Institute Poland & Institute of Fundamental Technological Research,Warsaw,Poland,02-105"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref2","article-title":"The Grid Audio-Visual Speech Corpus","volume":"1","author":"Cooke","year":"2006","journal-title":"Zenodo"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00121"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_41"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00955"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00502"},{"key":"ref9","article-title":"What is AI transparency?"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_31"},{"key":"ref11","article-title":"Talking Head Generation: A Survey","author":"Yao","year":"2023"},{"key":"ref12","article-title":"Training data-efficient image transformers and distillation through attention","volume-title":"ICML","author":"Touvron"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-19803-8_5","article-title":"TinyViT: Fast Pretraining Distillation for Small Vision Transformers","volume-title":"ICCV","author":"Wu"},{"key":"ref15","article-title":"Fast Transformer Decoding: One Write-Head is All You Need","author":"Shazeer","year":"2019"},{"key":"ref16","article-title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","volume-title":"ICLR","author":"Mehta"},{"key":"ref17","article-title":"Talking-Heads Attention","author":"Shazeer","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3630057"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_23"},{"key":"ref21","article-title":"RealTalk: Real-time and Realistic Audio-driven Face Generation with 3D Facial Prior-guided Identity Alignment","author":"Ji","year":"2024"},{"key":"ref22","article-title":"A Lightweight and High-Fidelity Model for Generalized Audio-Driven Facial Animation","volume-title":"ICPR","author":"Liu"}],"event":{"name":"2025 International Conference on Visual Communications and Image Processing (VCIP)","location":"Klagenfurt, Austria","start":{"date-parts":[[2025,12,1]]},"end":{"date-parts":[[2025,12,4]]}},"container-title":["2025 International Conference on Visual Communications and Image Processing (VCIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11396756\/11396790\/11396896.pdf?arnumber=11396896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:45:46Z","timestamp":1772005546000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11396896\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/vcip67698.2025.11396896","relation":{},"subject":[],"published":{"date-parts":[[2025,12,1]]}}}