{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:16:40Z","timestamp":1792081000551,"version":"4.4.0"},"reference-count":60,"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\/501100006355","name":"Shun Hing Institute of Advanced Engineering","doi-asserted-by":"publisher","award":["8115074"],"award-info":[{"award-number":["8115074"]}],"id":[{"id":"10.13039\/501100006355","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\/iccv51701.2025.01590","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17119-17128","source":"Crossref","is-referenced-by-count":1,"title":["HYPDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-Shot Image Generation"],"prefix":"10.1109","author":[{"given":"Lingxiao","family":"Li","sequence":"first","affiliation":[{"name":"MMLab, The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaixuan","family":"Fan","sequence":"additional","affiliation":[{"name":"MMLab, The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boqing","family":"Gong","sequence":"additional","affiliation":[{"name":"Boston University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangyu","family":"Yue","sequence":"additional","affiliation":[{"name":"MMLab, The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Data augmentation generative adversarial networks","author":"Antoniou","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Few-shot generative modelling with generative matching networks","author":"Bartunov","year":"2018","journal-title":"AISTATS"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2013.2254619"},{"key":"ref4","article-title":"Riemannian adaptive optimization methods","author":"B\u00e9cigneul","year":"2019","journal-title":"ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref6","first-page":"4868","article-title":"Christopher R\u00e9, and Jure Leskovec. Hyperbolic graph convolutional neural networks","author":"Chami","year":"2019","journal-title":"NeurIPS"},{"key":"ref7","article-title":"Subjectdriven text-to-image generation via apprenticeship learning","author":"Chen","year":"2023","journal-title":"NeurIPS"},{"key":"ref8","article-title":"Figr: Few-shot image generation with reptile","author":"Clou\u00e2tre","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00351"},{"key":"ref10","article-title":"Multiresolution textual inversion","volume-title":"NeurIPS Workshop","author":"Daras","year":"2022"},{"key":"ref11","first-page":"7694","article-title":"Hyperbolic image-text representations","volume-title":"ICML","author":"Desai","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-1708"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01091"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3578670"},{"key":"ref15","article-title":"Dreamartist: Towards controllable one-shot text-to-image generation via positivenegative prompt-tuning","author":"Dong","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref16","first-page":"5345","article-title":"Hyperbolic neural networks","author":"Ganea","year":"2018","journal-title":"NeurIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00661"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-9586-7_3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00835"},{"key":"ref20","article-title":"Highly personalized text embedding for image manipulation by stable diffusion","author":"Han","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00673"},{"key":"ref22","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_15"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102917"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413561"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_15"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548158"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00645"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref32","first-page":"176","volume-title":"Riemannian manifolds: an introduction to curvature","author":"Lee","year":"2006"},{"key":"ref33","volume-title":"Introduction to Smooth Manifolds","author":"Lee","year":"2013"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01862"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02076"},{"key":"ref36","article-title":"Dawson: A domain adaptive few shot generation framework","author":"Liang","journal-title":"arXiv preprint arXiv"},{"key":"ref37","article-title":"Few-shot unsueprvised image-to-image translation","author":"Liu","year":"2019","journal-title":"ICCV"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref39","article-title":"Generative visual manipulation on the natural image manifold","author":"Nickel","year":"2017","journal-title":"ECCV"},{"key":"ref40","article-title":"Learning continuous hierarchies in the lorentz model of hyperbolic geometry","author":"Nickel","year":"2018","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00547"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01036"},{"key":"ref45","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref46","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref50","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref51","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01242"},{"key":"ref53","article-title":"Poincar\u00e9 glove: Hyperbolic word embeddings","author":"Tifrea","year":"2019","journal-title":"ICLR"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"ref55","article-title":"P+: Extended textual conditioning in text-to-image generation","author":"Voynov","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_1"},{"key":"ref57","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arxiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00319"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00801"}],"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\/11444398.pdf?arnumber=11444398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:51:53Z","timestamp":1777611113000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01590","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}