{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T05:51:02Z","timestamp":1781761862421,"version":"3.54.5"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":"crossref","award":["U22A2063"],"award-info":[{"award-number":["U22A2063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Liaoning Provincial Science and Technology Program","doi-asserted-by":"publisher","award":["2023JH1\/10400045"],"award-info":[{"award-number":["2023JH1\/10400045"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3700933","type":"journal-article","created":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T20:03:41Z","timestamp":1781208221000},"page":"6305-6316","source":"Crossref","is-referenced-by-count":0,"title":["Global and Local Visual\u2013Textual Alignment for Open Vocabulary Object Detection"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6956-7342","authenticated-orcid":false,"given":"Hao","family":"Wang","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1424-798X","authenticated-orcid":false,"given":"Tong","family":"Jia","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6863-8516","authenticated-orcid":false,"given":"Shizhuo","family":"Deng","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0673-6767","authenticated-orcid":false,"given":"Dongyue","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3765-9787","authenticated-orcid":false,"given":"Qilong","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3330-783X","authenticated-orcid":false,"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3032166"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3263557"},{"key":"ref5","first-page":"1","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","volume-title":"Proc. ICLR","author":"Gu"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01368"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01072"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01464"},{"key":"ref11","first-page":"1","article-title":"Open-vocabulary object detection upon frozen vision and language models","volume-title":"Proc. ICLR","author":"Kuo"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00679"},{"key":"ref15","first-page":"1","article-title":"Learning object-language alignments for open-vocabulary object detection","volume-title":"Proc. ICLR","author":"Lin"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref19","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. ICML","author":"Jia"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2448"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00598"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00275"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref26","article-title":"Prompt-guided transformers for end-to-end open-vocabulary object detection","author":"Song","year":"2023","journal-title":"arXiv:2303.14386"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3293484"},{"key":"ref28","first-page":"9125","article-title":"DetCLIP: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume-title":"Proc. NIPS","author":"Yao"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02250"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01441"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3364495"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3459589"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3551648"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3485518"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01578"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01584"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.07155"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref40","first-page":"22682","article-title":"Aligning pretraining for detection via object-level contrastive learning","volume-title":"Proc. NIPS","author":"Wei"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00647"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00015"},{"issue":"86","key":"ref44","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"JMLR"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_7"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_16"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01076"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01606"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01322"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3113"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11559221.pdf?arnumber=11559221","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:51:39Z","timestamp":1781758299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11559221\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3700933","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}