{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T07:11:06Z","timestamp":1770880266144,"version":"3.50.1"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"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":[[2025,10,27]]},"DOI":"10.1109\/icves65691.2025.11376443","type":"proceedings-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:54:58Z","timestamp":1770843298000},"page":"15-20","source":"Crossref","is-referenced-by-count":0,"title":["Label Anything, Train Nothing: 2D Zero-Shot Annotation via Generative VLMs, Zero-Shot Object Detectors and Foundation Models"],"prefix":"10.1109","author":[{"given":"Daniel Serrano","family":"Dominguez","sequence":"first","affiliation":[{"name":"Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain"}]},{"given":"Alejandro Salazar","family":"Gomez","sequence":"additional","affiliation":[{"name":"Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain"}]},{"given":"Alejandro","family":"Barrera","sequence":"additional","affiliation":[{"name":"Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain"}]},{"given":"Jaime","family":"Godoy","sequence":"additional","affiliation":[{"name":"Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain"}]},{"given":"Fernando","family":"Garcia","sequence":"additional","affiliation":[{"name":"Universidad Carlos III de Madrid,Autonomous Mobility and Perception Lab (AMPL),Departamento de Ingeniería de Sistemas y Automática,Madrid,Spain"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0090-8"},{"key":"ref2","article-title":"Computer vision annotation tool (cvat)","year":"2020"},{"key":"ref3","article-title":"The cost of training vision models","author":"Rojas","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.47"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540054"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx106"},{"key":"ref7","article-title":"Label-efficient deep learning: A survey","author":"Tian","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref9","article-title":"Detclip: Dictionary-enriched visual-concept parallels for open-vocabulary detection","author":"Zhong","year":"2022","journal-title":"NeurIPS"},{"key":"ref10","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref12","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref13","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, and conversation","year":"2023"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.00695","article-title":"Image segmentation using text and image prompts","author":"L\u00fcddecke","year":"2022"},{"key":"ref15","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51070.2023.00371","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"ref17","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024"},{"issue":"13","key":"ref18","article-title":"Confidence score: The forgotten dimension of object detection performance evaluation","volume-title":"Sensors","volume":"21","author":"Wenkel","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635940"},{"key":"ref20","article-title":"Probability-based detection quality (pdq): A probabilistic approach to detection evaluation","volume-title":"ArXiv","author":"Hall","year":"2018"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01234-2_31","article-title":"Localization recall precision (lrp): A new performance metric for object detection","author":"Oksuz","year":"2018"}],"event":{"name":"2025 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","location":"Coventry, United Kingdom","start":{"date-parts":[[2025,10,27]]},"end":{"date-parts":[[2025,10,28]]}},"container-title":["2025 IEEE International Conference on Vehicular Electronics and Safety (ICVES)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373934\/11375868\/11376443.pdf?arnumber=11376443","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T06:29:33Z","timestamp":1770877773000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11376443\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icves65691.2025.11376443","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]}}}