{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:24Z","timestamp":1778051544358,"version":"3.51.4"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00617","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6381-6390","source":"Crossref","is-referenced-by-count":0,"title":["QUOTA: Quantifying Objects with Text-to-Image Models for Any Domain"],"prefix":"10.1109","author":[{"given":"Wenfang","family":"Sun","sequence":"first","affiliation":[{"name":"University of Amsterdam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingjun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaowen","family":"Liu","sequence":"additional","affiliation":[{"name":"Cisco Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yefeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"Westlake University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00233"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref4","article-title":"Flow matching in latent space","author":"Dao","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_12"},{"key":"ref6","first-page":"1126","article-title":"Modelagnostic meta-learning for fast adaptation of deep networks","volume-title":"ICML","author":"Finn"},{"key":"ref7","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"ICLR","author":"Gal"},{"key":"ref8","article-title":"Generative adversarial nets","volume-title":"NeurIPS","volume":"27","author":"Goodfellow"},{"key":"ref9","article-title":"Prompt-to-Prompt Image Editing with Cross-Attention Control","volume-title":"ICLR","author":"Hertz"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref11","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":"Advances in neural information processing systems"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","volume":"33","author":"Ho"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44668-0_13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00851"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00948"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11596"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00566"},{"key":"ref18","first-page":"3118","article-title":"Domain generalization for medical imaging classification with linear-dependency regularization","volume-title":"NeurIPS","volume":"33","author":"Li"},{"key":"ref19","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"key":"ref21","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"ref23","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref24","author":"Ramesh","year":"2022","journal-title":"Hierarchical text-conditional image generation with clip latents"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref27","article-title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","volume-title":"NeurIPS","author":"Saharia"},{"key":"ref28","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01026"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00950"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1302751110"},{"key":"ref32","volume-title":"Learning to learn","author":"Thrun","year":"2012"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref34","first-page":"11351","article-title":"A bit more bayesian: Domain-invariant learning with uncertainty","volume-title":"ICML","author":"Xiao"},{"key":"ref35","article-title":"Iterative object count optimization for text-to-image diffusion models","author":"Zafar","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01557"},{"key":"ref37","article-title":"Learning to count objects in natural images for visual question answering","author":"Zhang","year":"2018"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3195549"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492716.pdf?arnumber=11492716","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:17:15Z","timestamp":1778048235000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492716\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00617","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}