{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:05:57Z","timestamp":1770743157422,"version":"3.49.0"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":"publisher","award":["U23A20313"],"award-info":[{"award-number":["U23A20313"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372471"],"award-info":[{"award-number":["62372471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Science Foundation for Distinguished Young Scholars of Hunan Province","award":["2023JJ10080"],"award-info":[{"award-number":["2023JJ10080"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tvcg.2025.3633870","type":"journal-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T18:42:26Z","timestamp":1763750546000},"page":"68-78","source":"Crossref","is-referenced-by-count":0,"title":["OW-CLIP: Data-Efficient Visual Supervision for Open-World Object Detection via Human-AI Collaboration"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4955-9270","authenticated-orcid":false,"given":"Junwen","family":"Duan","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyao","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4499-6420","authenticated-orcid":false,"given":"Shixia","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Tsinghua University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4629-6268","authenticated-orcid":false,"given":"Jiazhi","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298799"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-023-00581-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3138933"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.2307\/249008"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2023.1166120"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"issue":"10.5555","key":"ref11","first-page":"2969239","article-title":"Towards real-time object detection with region proposal networks","volume":"9199","author":"Faster","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3240003"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00915"},{"key":"ref14","article-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00902"},{"key":"ref16","article-title":"Learning the k in k-means","volume":"16","author":"Hamerly","year":"2003","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3703155"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3326577"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114793"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00577"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00322"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref26","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2864843"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01044"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3394053"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.710"},{"key":"ref36","volume-title":"OpenAI. Hello gpt-4o","year":"2024"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01755"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref40","article-title":"Exploiting cloze questions for few shot text classification and natural language inference","author":"Schick","year":"2020","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Unseen class discovery in open-world classification","author":"Shu","year":"2018","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.12792\/iciae2015.012"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01976-7"},{"issue":"11","key":"ref44","article-title":"Visualizing data using t-sne","volume":"9","author":"Van","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref45","article-title":"Gpt-ner: Named entity recognition via large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00573"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01100"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01139"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00046"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114694"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/VAST47406.2019.8986943"},{"key":"ref54","article-title":"Hallucination is inevitable: An innate limitation of large language models","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Qwen2. 5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Objects in semantic topology","author":"Yang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref57","first-page":"9125","article-title":"Detclip: Dictionary-enriched visual-concept paralleled pre-training for open-world detection","volume":"35","author":"Yao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326279"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00441"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref62","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29670"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11373125\/11264329.pdf?arnumber=11264329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T00:33:22Z","timestamp":1770683602000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11264329\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":63,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3633870","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}