{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:31:31Z","timestamp":1785857491954,"version":"3.56.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403361"],"award-info":[{"award-number":["62403361"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tits.2024.3510117","type":"journal-article","created":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T14:30:59Z","timestamp":1734359459000},"page":"17510-17521","source":"Crossref","is-referenced-by-count":6,"title":["Zone-YOLO: Vision-Language Object Detection Using Zone Prompt"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7499-2474","authenticated-orcid":false,"given":"Jiaxiong","family":"Yang","sequence":"first","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2395-3432","authenticated-orcid":false,"given":"Ning","family":"Jia","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5088-3628","authenticated-orcid":false,"given":"Xianhui","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2593-6596","authenticated-orcid":false,"given":"Rui","family":"Fan","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1549-0108","authenticated-orcid":false,"given":"Yougang","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Rail Transit and the National Maglev Transportation Engineering Research and Development Center, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Electronics and Information Engineering, Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3285035"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3158253"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3350920"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3293822"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2024.103902"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-023-3968-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.02976"},{"key":"ref8","volume-title":"Ultralytics YOLO","author":"Jocher","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"ref10","article-title":"YOLOv10: Real-time end-to-end object detection","author":"Wang","year":"2024","journal-title":"arXiv:2405.14458"},{"key":"ref11","article-title":"PP-YOLOE: An evolved version of YOLO","author":"Xu","year":"2022","journal-title":"arXiv:2203.16250"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3381175"},{"key":"ref14","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3369699"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref20","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv:2104.13921"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"ref23","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611803"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02226"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.763"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277791"},{"key":"ref30","article-title":"PVLR: Prompt-driven visual-linguistic representation learning for multi-label image recognition","author":"Tan","year":"2024","journal-title":"arXiv:2401.17881"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3146575"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3293484"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25261"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01297"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00271"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00030"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref46","article-title":"Evaluating large-vocabulary object detectors: The devil is in the details","author":"Dave","year":"2021","journal-title":"arXiv:2102.01066"},{"key":"ref47","volume-title":"MMYOLO: OpenMMLab YOLO Series Toolbox and Benchmark","author":"Contributors","year":"2022"},{"key":"ref48","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.23977\/acss.2023.070812"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11220917\/10803284.pdf?arnumber=10803284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:52:08Z","timestamp":1770411128000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10803284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":50,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tits.2024.3510117","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}