{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T01:11:24Z","timestamp":1779153084646,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00188","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1885-1894","source":"Crossref","is-referenced-by-count":1,"title":["Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models"],"prefix":"10.1109","author":[{"given":"Oz","family":"Zafar","sequence":"first","affiliation":[{"name":"Tel-Aviv University,Tel Aviv,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuval","family":"Cohen","sequence":"additional","affiliation":[{"name":"Tel-Aviv University,Tel Aviv,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lior","family":"Wolf","sequence":"additional","affiliation":[{"name":"Tel-Aviv University,Tel Aviv,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Idan","family":"Schwartz","sequence":"additional","affiliation":[{"name":"Tel-Aviv University,Tel Aviv,Israel"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01236"},{"key":"ref2","article-title":"Training diffusion models with reinforcement learning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Black"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_5"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1229"},{"key":"ref8","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gal"},{"key":"ref9","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref11","article-title":"Prompt-to-Prompt Image Editing with Cross-Attention Control","volume-title":"The Eleventh International Conference on Learning Representations","author":"Hertz"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref13","article-title":"Classifier-Free Diffusion Guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref14","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/machines11070677"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611789"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00097"},{"key":"ref18","article-title":"Diffusionclip: Text-guided image manipulation using diffusion models","author":"Kim","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00585"},{"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","first-page":"8748","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18-24 July 2021, Virtual Event","author":"Radford"},{"key":"ref25","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref31","first-page":"4695","article-title":"Generating images of rare concepts using pretrained diffusion models","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Samuel"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_6"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02077"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1302751110"},{"key":"ref35","article-title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"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":"10.52202\/075280-0491"}],"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\/11492098.pdf?arnumber=11492098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:54:04Z","timestamp":1778046844000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00188","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}