{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:12Z","timestamp":1777865532453,"version":"3.51.4"},"reference-count":85,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00968","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10398-10409","source":"Crossref","is-referenced-by-count":0,"title":["Expressive Talking Human from Single-Image with Imperfect Priors"],"prefix":"10.1109","author":[{"given":"Jun","family":"Xiang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yudong","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leipeng","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boyang","family":"Guo","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yancheng","family":"Yuan","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00902"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618153"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01139"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01626"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_19"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01370"},{"key":"ref9","first-page":"arXiv2312","article-title":"Dreamoving: A human video generation framework based on diffusion models","author":"Feng","year":"2023","journal-title":"arXiv e-prints"},{"key":"ref10","article-title":"Livepor-trait: Efficient portrait animation with stitching and retargeting control","author":"Guo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356571"},{"key":"ref12","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-toimage diffusion models without specific tuning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459749"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3132237"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00058"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00060"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01012"},{"key":"ref18","article-title":"Expressive gaussian human avatars from monocular rgb video","author":"Hu","year":"2024","journal-title":"NeurIPS"},{"key":"ref19","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00067"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00858"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01930"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00824"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00152"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00668"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3592415"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00552"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01207"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_24"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01866"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00055"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417861"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01879"},{"key":"ref36","article-title":"Pshuman: Photorealistic single-view human reconstruction using cross-scale diffusion","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480528"},{"key":"ref39","article-title":"Human-vdm: Learning single-image 3d human gaussian splatting from video diffusion models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_47"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_2"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00081"},{"key":"ref44","article-title":"Humansplat: Generalizable single-image human gaussian splatting with structure priors","author":"Pan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00117"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3306078"},{"key":"ref48","article-title":"Controlnext: Powerful and efficient control for image and video generation","author":"Peng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00894"},{"key":"ref50","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00480"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01970"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00159"},{"key":"ref58","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Animate-x: Universal character image animation with enhanced motion representation","author":"Tan","year":"2025","journal-title":"ICLR 2025"},{"key":"ref60","article-title":"Dreamgaussian: Generative gaussian splatting for efficient 3d content creation","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00521"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01965"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4592-3"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01573"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618136"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00177"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00852"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01294"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00057"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3687771"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00077"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793720"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00181"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref77","article-title":"Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00948"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00759"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.26599\/AIR.2024.9150038"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01861"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3050505"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02450"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00095"}],"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\/11445038.pdf?arnumber=11445038","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:35Z","timestamp":1777531595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445038\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00968","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}