{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T23:11:00Z","timestamp":1768518660297,"version":"3.49.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T00:00:00Z","timestamp":1765670400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302265,U23A20332"],"award-info":[{"award-number":["62302265,U23A20332"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"publisher","award":["ZR2023QF172,2024HWYQ-020"],"award-info":[{"award-number":["ZR2023QF172,2024HWYQ-020"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,14]]},"DOI":"10.1109\/icpads67057.2025.11323182","type":"proceedings-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:36:54Z","timestamp":1768423014000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["FastAvatar: Enabling Fast Talking-Face Synthesis on Resource-Constrained Devices via Multimodal Caching and Adaptation"],"prefix":"10.1109","author":[{"given":"Runzheng","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Shandong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahua","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Lu","sequence":"additional","affiliation":[{"name":"New York University,Department of Computer Science,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Modern Finance, Jiaxing Nanhu University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanle","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"What comprises a good talking-head video generation?: A survey and benchmark","author":"Chen","year":"2020","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"A comprehensive taxonomy and analysis of talking head synthesis: Techniques for portrait generation, driving mechanisms, and editing","author":"Meng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3448104"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2015.19"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486411"},{"key":"ref6","article-title":"Dreamtalk: When expressive talking head generation meets diffusion probabilistic models","author":"Ma","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01621"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681328"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221968"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw53098.2021.00271"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"ref22","article-title":"Neural-enhanced volumetric video streaming","volume-title":"USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Zhang","year":"2022"},{"key":"ref23","article-title":"Neural adaptive contentaware internet video delivery","volume-title":"USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Yeo","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3651890.3672274"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlposs-1.24"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241563"},{"key":"ref27","article-title":"Viva: An end-to-end system for interactive video analytics","volume-title":"Proceedings of the Conference on Innovative Data Systems Research (CIDR)","author":"Kang","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref29","article-title":"Approximate caching for efficiently serving text-to-image diffusion models","volume-title":"USENIX Symposium on Networked Systems Design and Implementation (NSDI)","author":"Agarwal","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref31","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Learning audio-driven viseme dynamics for 3d face animation","author":"Bao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414026"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100274"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100239"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2006.1580151"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tbdata.2025.3618474"}],"event":{"name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","location":"Hefei, China","start":{"date-parts":[[2025,12,14]]},"end":{"date-parts":[[2025,12,18]]}},"container-title":["2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11322805\/11322871\/11323182.pdf?arnumber=11323182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T07:17:35Z","timestamp":1768461455000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11323182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icpads67057.2025.11323182","relation":{},"subject":[],"published":{"date-parts":[[2025,12,14]]}}}