{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T20:03:50Z","timestamp":1779912230179,"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\/iccv51701.2025.01127","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12124-12134","source":"Crossref","is-referenced-by-count":1,"title":["DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation"],"prefix":"10.1109","author":[{"given":"Donglin","family":"Di","sequence":"first","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Feng","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzhang","family":"Sun","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjia","family":"Ma","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Li Auto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Fan","sequence":"additional","affiliation":[{"name":"University of New South Wales"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tonghua","family":"Su","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Paddleocr, awesome multilingual ocr toolkits based on paddlepaddle","volume-title":"PaddlePaddle Authors","year":"2020"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv:2311.15127"},{"key":"ref3","article-title":"GPAvatar: Generalizable and precise head avatar from image(s)","author":"Chu","year":"2024","journal-title":"ICLR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54184-6_6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1929"},{"key":"ref7","article-title":"Hallo2: Long-duration and high-resolution audio-driven portrait image animation","author":"Cui","year":"2024","journal-title":"arXiv:2410.07718"},{"key":"ref8","article-title":"Hallo3: Highly dynamic and realistic portrait image animation with diffusion transformer networks","author":"Cui","year":"2024","journal-title":"arXiv:2412.00733"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01964"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02133"},{"key":"ref11","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02298-y"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00489"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00812"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02044"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02660-8"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02376"},{"key":"ref18","article-title":"One-shot pose-driving face animation platform","author":"Feng","year":"2024","journal-title":"arXiv:2407.08949"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"ref20","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Liveportrait: Efficient portrait animation with stitching and retargeting control","author":"Guo","year":"2024","journal-title":"arXiv:2407.03168"},{"key":"ref22","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2024","journal-title":"ICLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2021.3132237"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref25","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02108"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"ref29","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv:2205.15868"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2024.3497725"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00842"},{"key":"ref32","article-title":"Video-lavit: Unified video-language pre-training with decoupled visual-motional tokenization","author":"Jin","year":"2024","journal-title":"arXiv:2402.03161"},{"key":"ref33","article-title":"Latentsync: Audio conditioned latent diffusion models for lip sync","author":"Li","year":"2024","journal-title":"arXiv:2412.09262"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"ref35","article-title":"Emotional conversation: Empowering talking faces with cohesive expression, gaze and pose generation","author":"Liang","year":"2024","journal-title":"arXiv:2406.07895"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02104"},{"key":"ref37","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv:2401.03048"},{"key":"ref38","article-title":"Follow-youremoji: Fine-controllable and expressive freestyle portrait animation","author":"Ma","year":"2024","journal-title":"arXiv:2406.01900"},{"key":"ref39","article-title":"Adams bashforth moulton solver for inversion and editing in rectified flow","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2214050"},{"key":"ref41","article-title":"Facexformer: A unified transformer for facial analysis","author":"Narayan","year":"2024","journal-title":"arXiv:2403.12960"},{"key":"ref42","article-title":"Precise localization of memories: A fine-grained neuron-level knowledge editing technique for 11 ms","author":"Pan","year":"2025","journal-title":"ICLR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00006"},{"key":"ref45","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref46","article-title":"Consisti2v: Enhancing visual consistency for image-to-video generation","author":"Ren","year":"2024","journal-title":"arXiv:2402.04324"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref50","article-title":"First order motion model for image animation","volume":"32","author":"Siarohin","year":"2019","journal-title":"NeurIPS"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref52","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00502"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28314"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28313"},{"key":"ref56","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref57","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv:1812.01717"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref60","article-title":"Text-tovideo: a two-stage framework for zero-shot identity-agnostic talking-head generation","author":"Wang","year":"2023","journal-title":"arXiv:2308.06457"},{"key":"ref61","article-title":"Aniportrait: Audio-driven synthesis of photorealistic portrait animation","volume-title":"arXiv:2403.17694","author":"Wei","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"ref63","article-title":"Easyanimate: A high-performance long video generation method based on transformer architecture","author":"Xu","year":"2024","journal-title":"arXiv:2405.18991"},{"key":"ref64","article-title":"Pllava: Parameter-free llava extension from images to videos for video dense captioning","author":"Xu","year":"2024","journal-title":"arXiv:2404.16994"},{"key":"ref65","article-title":"Vasa-1: Lifelike audio-driven talking faces generated in real time","author":"Xu","year":"2024","journal-title":"arXiv:2404.10667"},{"key":"ref66","article-title":"Megactor: Harness the power of raw video for vivid portrait animation","author":"Yang","year":"2024","journal-title":"arXiv:2405.20851"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-4084-6"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref71","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv:2408.06072"},{"key":"ref72","article-title":"Real3d-portrait: One-shot realistic 3d talking portrait synthesis","volume-title":"ICLR","author":"Ye","year":"2024"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01422"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00070"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747380"},{"key":"ref76","volume-title":"I2vgenxl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00366"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref79","author":"Zheng","year":"2024","journal-title":"Opensora: Democratizing efficient video production for all"},{"key":"ref80","article-title":"Towards robust blind face restoration with codebook lookup transformer","author":"Zhou","year":"2022","journal-title":"NeurIPS"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00319"},{"key":"ref82","first-page":"650","article-title":"Celebvhq: A large-scale video facial attributes dataset","volume-title":"ECCV","author":"Zhu","year":"2022"}],"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\/11449021.pdf?arnumber=11449021","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:33:44Z","timestamp":1777613624000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449021\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01127","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}