{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:18:21Z","timestamp":1777889901505,"version":"3.51.4"},"reference-count":59,"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\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["OAC-2118240"],"award-info":[{"award-number":["OAC-2118240"]}],"id":[{"id":"10.13039\/100000001","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\/iccv51701.2025.00803","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8579-8589","source":"Crossref","is-referenced-by-count":0,"title":["Taxadiffusion: Progressively Trained Diffusion Model for Fine-Grained Species Generation"],"prefix":"10.1109","author":[{"given":"Amin Karimi","family":"Monsefi","sequence":"first","affiliation":[{"name":"The Ohio State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mridul","family":"Khurana","sequence":"additional","affiliation":[{"name":"Virginia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajiv","family":"Ramnath","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anuj","family":"Karpatne","sequence":"additional","affiliation":[{"name":"Virginia Tech"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Lun","family":"Chao","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Texas A&M University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00389"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1267"},{"key":"ref3","article-title":"Very deep vaes generalize autoregressive models and can outperform them on images","author":"Child","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref4","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.11646\/zootaxa.1519.1.3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref7","article-title":"A step towards worldwide biodiversity assessment: The bioscan- 1 m insect dataset","volume":"36","author":"Gharaee","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref8","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"Highly personalized text embedding for image manipulation by stable diffusion","author":"Han","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2021","journal-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications"},{"key":"ref11","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s13127-021-00516-w"},{"key":"ref14","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3541625"},{"key":"ref16","article-title":"Guiding a diffusion model with a bad version of itself","author":"Karras","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01874"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73024-5_9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref20","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref21","first-page":"129","article-title":"Controlnet++: Improving conditional controls with efficient consistency feedback","volume-title":"European Conference on Computer Vision","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109200"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00213"},{"key":"ref24","article-title":"Fine-grained image editing by pixel-wise guidance using diffusion models","author":"Matsunaga","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref25","article-title":"Detailclip: Detail-oriented clip for fine-grained tasks","author":"Karimi Monsefi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","article-title":"Knobgen: Controlling the sophistication of artwork in sketch-based diffusion models","author":"Navard","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref27","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1186\/1742-9994-7-16"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-06215-1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_27"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01383"},{"key":"ref33","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"2","key":"ref35","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":"ref36","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref42","volume-title":"pytorch-fid: FID Score for PyTorch.","author":"Seitzer","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01836"},{"key":"ref44","first-page":"472","article-title":"An empirical study and analysis of text-to-image generation using large language model-powered textual representation","volume-title":"European Conference on Computer Vision","author":"Tan"},{"key":"ref45","first-page":"19667","article-title":"Nvae: A deep hierarchical variational autoencoder","volume":"33","author":"Vahdat","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref47","article-title":"Animatelcm: Accelerating the animation of personalized diffusion models and adapters with decoupled consistency learning","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00807"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00441"},{"key":"ref51","article-title":"Fine-grained appearance transfer with diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref52","article-title":"Chatface: Chat-guided real face editing via diffusion latent space manipulation","author":"Yue","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657396"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00367"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1563-3"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00584"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"}],"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\/11445839.pdf?arnumber=11445839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:23:22Z","timestamp":1777613002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445839\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00803","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}