{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:16:04Z","timestamp":1777889764943,"version":"3.51.4"},"reference-count":58,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62402157"],"award-info":[{"award-number":["62402157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JZ2025HGTB0219"],"award-info":[{"award-number":["JZ2025HGTB0219"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100031478","name":"NextGenerationEU","doi-asserted-by":"publisher","award":["101120237"],"award-info":[{"award-number":["101120237"]}],"id":[{"id":"10.13039\/100031478","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\/iccv51701.2025.00108","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1078-1087","source":"Crossref","is-referenced-by-count":0,"title":["Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Liu","sequence":"first","affiliation":[{"name":"Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nan","family":"Pu","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyang","family":"Zheng","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjing","family":"Li","sequence":"additional","affiliation":[{"name":"Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicu","family":"Sebe","sequence":"additional","affiliation":[{"name":"University of Trento"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhun","family":"Zhong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26475"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00166"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2571"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01125"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0749"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00255"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00915"},{"key":"ref9","article-title":"Dreamda: Generative data augmentation with diffusion models","author":"Fu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00849"},{"key":"ref12","volume-title":"Clustering algorithms","author":"Hartigan","year":"1975"},{"key":"ref13","article-title":"Is synthetic data from generative models ready for image recognition?","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02608"},{"key":"ref16","article-title":"Podia3d: Domain adaptation of 3d generative model across large domain gap using pose-preserved text-to-image diffusion","volume-title":"ICCV","author":"Kim","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01530"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref20","article-title":"Diffusion models already have A semantic latent space","volume-title":"ICLR","author":"Kwon","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00210"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01612"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01674"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104197"},{"key":"ref25","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3424985"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00732"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02715"},{"key":"ref30","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"issue":"2","key":"ref31","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1140\/epjst\/e2010-01179-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00084"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/325334.325242"},{"key":"ref37","article-title":"Latent space disentanglement in diffusion transformers enables zero-shot fine-grained semantic editing","author":"Shuai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Effective data augmentation with diffusion models","author":"Trabucco","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_15"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00734"},{"key":"ref42","article-title":"The caltech-ucsd birds-200-2011 dataset","volume-title":"Computation & Neural Systems Technical Report","author":"Wah","year":"2011"},{"key":"ref43","article-title":"Videocomposer: Compositional video synthesis with motion controllability","volume-title":"NeurIPS","author":"Wang","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01630"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01521"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00159"},{"key":"ref47","article-title":"Learning to distinguish samples for generalized category discovery","volume-title":"ECCV","author":"Yang","year":"2024"},{"key":"ref48","article-title":"Diffusion models and semi-supervised learners benefit mutually with few labels","volume-title":"NeurIPS","author":"You","year":"2024"},{"key":"ref49","article-title":"Coca: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref51","article-title":"Mixup: Beyond 903 empirical risk minimization","volume-title":"ICLR","author":"Zhang","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01753"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00871"},{"key":"ref54","article-title":"Textual knowledge matters: Cross-modality coteaching for generalized visual class discovery","volume-title":"ECCV","author":"Zheng","year":"2024"},{"key":"ref55","article-title":"Prototypical hash encoding for on-the-fly fine-grained category discovery","volume-title":"NeurIPS","author":"Zheng","year":"2025"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01072"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28598"},{"key":"ref58","article-title":"Training on thin air: Improve image classification with generated data","author":"Zhou","year":"2023","journal-title":"arXiv preprint"}],"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\/11445224.pdf?arnumber=11445224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:19:06Z","timestamp":1777612746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00108","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}