{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T00:47:02Z","timestamp":1774658822806,"version":"3.50.1"},"reference-count":50,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890615","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Identity-Preserving Audio-Driven Holistic Human Motion Video Generation"],"prefix":"10.1109","author":[{"given":"Haiwei","family":"Xue","sequence":"first","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhensong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Noah’s Ark Lab,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minglei","family":"Li","sequence":"additional","affiliation":[{"name":"01.AI,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zonghong","family":"Dai","sequence":"additional","affiliation":[{"name":"Institute of Fudan University,Artificial Intelligence Innovation and Incubation (Al’),Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyong","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/237170.237258"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/192161.192272"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2013.09.008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3407692"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417838"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00190"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14776"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/002383099403700208"},{"key":"ref9","article-title":"Styletalker: One-shot style-based audio-driven talking head video generation","author":"Min","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.5220\/0012312200003636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3570945.3607337"},{"key":"ref13","article-title":"Audio-driven co-speech gesture video generation","volume-title":"NeurIPS","author":"Liu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342027"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/650"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27919"},{"key":"ref18","article-title":"A unified framework for multimodal, multi-part human motion synthesis","author":"Zhou","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02300-7"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00101"},{"key":"ref21","article-title":"Posetalk: Text-and-audio-based pose control and motion refinement for one-shot talking head generation","author":"Ling","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681238"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00917"},{"key":"ref26","article-title":"Lumi\u00e8renet: Lecture video synthesis from audio","author":"Kim","year":"2019"},{"key":"ref27","article-title":"Video-to-video synthesis","volume-title":"NeurIPS","author":"Wang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00249"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"ref30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-69541-5_19","article-title":"Speech2video synthesis with 3d skeleton regularization and expressive body poses","volume-title":"ACCV","author":"Liao"},{"key":"ref31","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref33","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref35","article-title":"Openmmlab pose estimation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2207676.2208639"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref38","article-title":"Auto-encoding variational bayes","volume-title":"ICLR","author":"Kingma"},{"key":"ref39","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"ICML","author":"Chen"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00319"},{"key":"ref41","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell"},{"key":"ref42","article-title":"FVD: A new metric for video generation","volume-title":"ICLR","author":"Unterthiner"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1049\/el:20080522"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"ref47","article-title":"Magicdance: Realistic human dance video generation with motions & facial expressions transfer","author":"Chang","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00668"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890615.pdf?arnumber=10890615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:50Z","timestamp":1774416170000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890615","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}