{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:21Z","timestamp":1778051541557,"version":"3.51.4"},"reference-count":50,"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\/501100016134","name":"FRAME","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100016134","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\/wacv61042.2026.00079","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"740-750","source":"Crossref","is-referenced-by-count":0,"title":["Can We Challenge Open-Vocabulary Object Detectors with Generated Content in Street Scenes?"],"prefix":"10.1109","author":[{"given":"Annika","family":"M\u00fctze","sequence":"first","affiliation":[{"name":"Osnabrück University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sadia","family":"Ilyas","sequence":"additional","affiliation":[{"name":"Aptiv Services Deutschland GmbH,Wuppertal,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chrsitian","family":"D\u00f6rpelkus","sequence":"additional","affiliation":[{"name":"University of Wuppertal,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthias","family":"Rottmann","sequence":"additional","affiliation":[{"name":"Osnabrück University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06430-2_59"},{"key":"ref2","volume-title":"Stable Diffusion Web UI","year":"2022"},{"key":"ref3","volume-title":"Improving image generation with better captions","author":"Betker","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02125"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01511-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"ref9","article-title":"Vos: Learning what you don\u2019t know by virtual outlier synthesis","author":"Du","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/rs16020327"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91672-4_13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00180"},{"key":"ref14","article-title":"Imagenhub: Standardizing the evaluation of conditional image generation models","author":"Ku","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00071"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref18","article-title":"Utilizing synthetic data for medical vision-language pretraining: Bypassing the need for real images","author":"Liu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_25"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref24","volume-title":"Dreamshaper (revision 8c1bfc6)","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00583"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460700"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793821"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3359"},{"key":"ref31","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref32","article-title":"How much real data do we actually need: Analyzing object detection performance using synthetic and real data","author":"Nowruzi","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759186"},{"issue":"2","key":"ref34","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00391"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IVWorkshops54471.2021.9669248"},{"key":"ref39","volume-title":"Stable Diffusion Inpainting","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534289"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref43","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02154"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02148"},{"key":"ref46","article-title":"Ipadapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2614"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref49","article-title":"Real-time transformer-based open-vocabulary detection with efficient fusion head","author":"Zhao","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"}],"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\/11492662.pdf?arnumber=11492662","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:16:52Z","timestamp":1778048212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492662\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00079","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}