{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T10:19:12Z","timestamp":1773137952997,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"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":["62206077"],"award-info":[{"award-number":["62206077"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Inner Mongolia Natural Science Foundation for Distinguished Young Scholars","award":["2025JQ009"],"award-info":[{"award-number":["2025JQ009"]}]},{"name":"Inner Mongolia Talent Development Project for Outstanding Young Talents"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tcsvt.2025.3613389","type":"journal-article","created":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T17:35:21Z","timestamp":1758735321000},"page":"2814-2829","source":"Crossref","is-referenced-by-count":0,"title":["ILD: Image-Level Labels Driven Active Learning Object Detection"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9723-6797","authenticated-orcid":false,"given":"Rui","family":"Tian","sequence":"first","affiliation":[{"name":"School of Instrumentation Science and Engineering, Harbin Institute of Technology (HIT), Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0158-0251","authenticated-orcid":false,"given":"Jiaxuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Instrumentation Science and Engineering, Harbin Institute of Technology (HIT), Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0437-7337","authenticated-orcid":false,"given":"Yongqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science (College of Software-College of Artificial Intelligence), Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8048-7247","authenticated-orcid":false,"given":"Man","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Instrumentation Science and Engineering, Harbin Institute of Technology (HIT), Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1907-1402","authenticated-orcid":false,"given":"Zian","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Instrumentation Science and Engineering, Harbin Institute of Technology (HIT), Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3860-9001","authenticated-orcid":false,"given":"Yin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Instrumentation Science and Engineering, Harbin Institute of Technology (HIT), Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Instrumentation Science and Engineering, Harbin Institute of Technology (HIT), Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology (HIT), Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01684"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01010"},{"key":"ref3","first-page":"48292","article-title":"STONE: A submodular optimization framework for active 3D object detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"37","author":"Mao"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_13"},{"key":"ref5","first-page":"6459","article-title":"ALWOD: Active learning for weakly-supervised object detection","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Yuting"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01409"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00918"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00529"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1175"},{"key":"ref10","first-page":"1","article-title":"Active learning for object detection with evidential deep learning and hierarchical uncertainty aggregation","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Park"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3288134"},{"key":"ref12","article-title":"MiniGPT-V2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv:2310.09478"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_18"},{"key":"ref14","article-title":"Qwen2.5-VL technical report","volume-title":"arXiv:2502.13923","author":"Bai","year":"2025"},{"key":"ref15","first-page":"72983","article-title":"Scaling open-vocabulary object detection","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"36","author":"Minderer"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_18"},{"key":"ref17","article-title":"Contrastive localized language-image pre-training","author":"Chen","year":"2024","journal-title":"arXiv:2410.02746"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3528108"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3396463"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref21","first-page":"1507","article-title":"Learning spatial similarity distribution for few-shot object counting","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Xu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00289"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107671"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1003111107"},{"key":"ref25","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref26","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref28","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref29","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01392"},{"key":"ref31","first-page":"728","article-title":"Simple open-vocabulary object detection with vision transformers","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Minderer"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3571422"},{"key":"ref33","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Wei"},{"key":"ref34","first-page":"1","article-title":"Training chain-of-thought via latent-variable inference","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"36","author":"Hoffman"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30364"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29884"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00285"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3524645"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29844"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168547"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28127"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00040"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.49"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680960"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3511621"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3532440"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref53","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhu"},{"key":"ref54","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2025.3584808"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP51287.2024.10647710"},{"key":"ref58","first-page":"1","article-title":"Active learning for convolutional neural networks: A core-set approach","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ozan"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3277738"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11424237\/11176953.pdf?arnumber=11176953","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T20:01:09Z","timestamp":1773086469000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11176953\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":59,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3613389","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}