{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:50:57Z","timestamp":1778082657849,"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\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["IIS-2127544,IIS-2433768"],"award-info":[{"award-number":["IIS-2127544,IIS-2433768"]}],"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\/iccv51701.2025.01557","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16765-16775","source":"Crossref","is-referenced-by-count":1,"title":["YOLO-Count: Differentiable Object Counting for Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Guanning","family":"Zeng","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"UC,San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zirui","family":"Wang","sequence":"additional","affiliation":[{"name":"UC,Berkeley"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyang","family":"Xu","sequence":"additional","affiliation":[{"name":"UC,San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"UC,San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingnan","family":"Li","sequence":"additional","affiliation":[{"name":"UC,San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuowen","family":"Tu","sequence":"additional","affiliation":[{"name":"UC,San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"510","article-title":"Open-world text-specifed object counting","author":"Amini-Naieni","year":"2023","journal-title":"BMVC"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1547"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10578-9_33"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_30"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657527"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/3477.775269"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01607"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00454"},{"key":"ref13","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"In The Eleventh International Conference on Learning Representations","author":"Gal"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02681"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref17","article-title":"Learning to count anything: Reference-less class-agnostic counting with weak supervision","author":"Hobley","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.446"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1408"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01615"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611789"},{"key":"ref23","author":"Jocher","year":"2023","journal-title":"Ultralytics yolov8"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28050"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00097"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref27","article-title":"Learning to count objects in images","volume-title":"In Advances in Neural Information Processing Systems","author":"Lempitsky","year":"2010"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00747"},{"key":"ref31","article-title":"Countr: Transformer-based generalised visual counting","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1049\/ic:19970387"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_20"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02198"},{"key":"ref36","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In Proceedings of the 38th International Conference on Machine Learning","author":"Radford"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"ref38","article-title":"Grounding dino 1.5: Advance the \u201cedge\u201d of open-set object detection","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-01990-3"},{"key":"ref41","year":"2024","journal-title":"Stability AI. Sdxl-turbo: Text-to-image generative model"},{"key":"ref42","article-title":"Quota: Quantifying objects with text-to-image models for any domain","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Nwpucrowd: A large-scale benchmark for crowd counting and localization","author":"Wang","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446636"},{"key":"ref45","article-title":"Gca-sun: A gated contextaware swin-unet for exemplar-free counting","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01492"},{"key":"ref48","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref50","article-title":"Iterative object count optimization for text-to-image diffusion models","author":"Zafar","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref53","article-title":"Loco: Locally constrained training-free layout-to-image synthesis","volume-title":"arXiv preprint arXiv","author":"Zhao","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref55","first-page":"7396973982","article-title":"Michelangelo: Conditional 3d shape generation based on shape-image-text aligned latent representation","volume-title":"In Advances in Neural Information Processing Systems","author":"Zhao","year":"2023"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_22"}],"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\/11444988.pdf?arnumber=11444988","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:25:23Z","timestamp":1777613123000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444988\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01557","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}