{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:57:59Z","timestamp":1777888679650,"version":"3.51.4"},"reference-count":66,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R &D Program of China","doi-asserted-by":"publisher","award":["2022ZD0160102"],"award-info":[{"award-number":["2022ZD0160102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206272"],"award-info":[{"award-number":["62206272"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01486","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16015-16025","source":"Crossref","is-referenced-by-count":0,"title":["Fontanimate: High Quality Few-Shot Font Generation Via Animating Font Transfer Process"],"prefix":"10.1109","author":[{"given":"Bin","family":"Fu","sequence":"first","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kainan","family":"Yan","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shitian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Qin","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Wen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjun","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00217"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_43"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref6","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref8","article-title":"Pixart-a: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"arxiv preprint arxiv","author":"Chen","year":"2023"},{"key":"ref9","article-title":"Dgfont++: Robust deformable generative networks for unsupervised font generation","author":"Chen","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref11","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in neural information processing systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref12","article-title":"Dreamartist: Towards controllable one-shot text-to-image generation via contrastive prompt-tuning","author":"Dong","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref13","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref14","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02149"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00658"},{"key":"ref17","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gal"},{"issue":"6","key":"ref18","first-page":"1","article-title":"Artistic glyph image synthesis via one-stage fewshot learning","volume-title":"ACM Transactions on Graphics (TOG)","volume":"38","author":"Gao","year":"2019"},{"key":"ref19","article-title":"Atomovideo: High fidelity image-to-video generation","author":"Gong","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref20","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref22","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02137-0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3382621"},{"key":"ref25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","article-title":"Progressive growing of gans for improved quality, stability, and variation","author":"Karras","year":"2017","journal-title":"arxiv preprint arxiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref28","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arxiv preprint arxiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01312"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02279"},{"key":"ref31","article-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining","author":"Liu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref32","first-page":"7905","article-title":"Xmpfont: Self-supervised cross-modality pre-training for fewshot font generation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu"},{"key":"ref33","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","volume-title":"arxiv preprint arxiv","author":"Meng","year":"2021"},{"key":"ref34","article-title":"Conditional generative adversarial nets","author":"Mirza","year":"2014","journal-title":"arxiv preprint arxiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref36","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref37","first-page":"16784","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01787"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01787"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16340"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01364"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"issue":"2","key":"ref43","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref48","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref49","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref50","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arxiv preprint arxiv"},{"key":"ref51","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref52","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume":"33","author":"Song","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref53","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arxiv preprint arxiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00774"},{"key":"ref55","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00185"},{"key":"ref57","article-title":"Pretraining is all you need for image-to-image translation","author":"Wang","year":"2022","journal-title":"arxiv preprint arxiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00509"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28482"},{"key":"ref62","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29577"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00881"},{"key":"ref66","article-title":"Lumina-next: Making lumina-t2x stronger and faster with next-dit","author":"Zhuo","year":"2024","journal-title":"arxiv preprint arxiv"}],"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\/11444907.pdf?arnumber=11444907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:54:31Z","timestamp":1777611271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444907\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01486","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}