{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T20:06:27Z","timestamp":1779912387389,"version":"3.53.1"},"reference-count":82,"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\/iccv51701.2025.01285","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13848-13858","source":"Crossref","is-referenced-by-count":6,"title":["OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models"],"prefix":"10.1109","author":[{"given":"Gaojie","family":"Lin","sequence":"first","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianwen","family":"Jiang","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zerong","family":"Zheng","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Liang","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingtuo","family":"Liu","sequence":"additional","affiliation":[{"name":"ByteDance Intelligent Creation"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"ref2","volume":"1","author":"Bai","year":"2023","journal-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref4","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2303"},{"key":"ref7","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref8","author":"Chen","year":"2024","journal-title":"Pixart-delta: Fast and controllable image generation with latent consistency models"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01482"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01964"},{"key":"ref14","article-title":"Patch n\u2019pack: Navit, a vision transformer for any aspect ratio and resolution","author":"Dehghani","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref15","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref17","author":"Guo","year":"2023","journal-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref19","author":"He","year":"2023","journal-title":"Gaia: Zero-shot talking avatar generation"},{"key":"ref20","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00198"},{"key":"ref24","author":"Hong","year":"2022","journal-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers"},{"key":"ref25","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":"ref26","author":"Jiang","year":"2024","journal-title":"Loopy: Taming audio-driven portrait avatar with long-term motion dependency"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01484"},{"key":"ref28","article-title":"Kaggle","volume-title":"Ravdess emotional speech audio"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref30","author":"Kondratyuk","year":"2023","journal-title":"Videopoet: A large language model for zero-shot video generation"},{"key":"ref31","author":"Kong","year":"2024","journal-title":"Hunyuanvideo: A systematic framework for large video generative models"},{"key":"ref32","article-title":"Black Forest Labs","volume-title":"Flux","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref34","article-title":"Cyberhost: A one-stage diffusion framework for audio-driven talking body generation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Lin","year":"2025"},{"key":"ref35","author":"Lin","year":"2025","journal-title":"Diffusion adversarial post-training for one-step video generation"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref37","author":"Liu","year":"2022","journal-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00516"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref42","author":"Polyak","year":"2024","journal-title":"Movie gen: A cast of media foundation models"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref45","author":"Shao","year":"2024","journal-title":"Human4dit: Free-view human video generation with 4d diffusion transformer"},{"key":"ref46","article-title":"First order motion model for image animation","author":"Siarohin","year":"2019","journal-title":"Advances in neural information processing systems, 32"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref48","author":"Singer","year":"2022","journal-title":"Make-a-video: Text-to-video generation without text-video data"},{"key":"ref49","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1142\/9789814354110_0008"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref53","author":"Tian","year":"2025","journal-title":"Emo2: End-effector guided audio-driven avatar video generation"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref55","author":"Touvron","year":"2023","journal-title":"Llama 2: Open foundation and fine-tuned chat models"},{"key":"ref56","volume-title":"Fvd: A new metric for video generation","author":"Unterthiner","year":"2019"},{"key":"ref57","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"International Conference on Learning Representations","author":"Villegas","year":"2022"},{"key":"ref58","author":"Wang","year":"2024","journal-title":"V-express: Conditional dropout for progressive training of portrait video generation"},{"key":"ref59","author":"Wang","year":"2024","journal-title":"V-express: Conditional dropout for progressive training of portrait video generation"},{"key":"ref60","author":"Wang","year":"2023","journal-title":"Modelscope text-to-video technical report"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093492"},{"key":"ref64","author":"Wu","year":"2023","journal-title":"Q-align: Teaching 1 mms for visual scoring via discrete text-defined levels"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00081"},{"key":"ref67","volume-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation","author":"Xu","year":"2024"},{"key":"ref68","author":"Xu","year":"2024","journal-title":"Vasa-1: Lifelike audio-driven talking faces generated in real time"},{"key":"ref69","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref70","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref71","article-title":"Geneface: Generalized and high-fidelity audio-driven 3d talking face synthesis","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ye","year":"2022"},{"key":"ref72","author":"Yu","year":"2023","journal-title":"Language model beats diffusion-tokenizer is key to visual generation"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00845"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref75","author":"Zhang","year":"2024","journal-title":"Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref77","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref78","volume-title":"Fada: Fast diffusion avatar synthesis with mixed-supervised multi-cfg distillation","author":"Zhong","year":"2024"},{"key":"ref79","author":"Zhou","year":"2022","journal-title":"Magicvideo: Efficient video generation with latent diffusion models"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_38"},{"key":"ref81","first-page":"10544","article-title":"Taming diffusion models for audiodriven co-speech gesture generation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhu","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"}],"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\/11445059.pdf?arnumber=11445059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:09Z","timestamp":1777612329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445059\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01285","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}