{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:45:57Z","timestamp":1781883957011,"version":"3.54.5"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["62076078"],"award-info":[{"award-number":["62076078"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Chinese Association for Artificial Intelligence -Huawei MindSpore Open Fund","doi-asserted-by":"publisher","award":["CAAIXSJLJJ-2020-033A"],"award-info":[{"award-number":["CAAIXSJLJJ-2020-033A"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3488721","type":"journal-article","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T13:38:48Z","timestamp":1730381928000},"page":"2487-2498","source":"Crossref","is-referenced-by-count":24,"title":["Zero-Shot Object Counting With Vision-Language Prior Guidance Network"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0996-6832","authenticated-orcid":false,"given":"Wenzhe","family":"Zhai","sequence":"first","affiliation":[{"name":"College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4159-1922","authenticated-orcid":false,"given":"Xianglei","family":"Xing","sequence":"additional","affiliation":[{"name":"College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7273-7499","authenticated-orcid":false,"given":"Mingliang","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Shandong University of Technology, Zibo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9675-9016","authenticated-orcid":false,"given":"Qilei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electrical and Electronic Engineering, Shandong University of Technology, Zibo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00309"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00479"},{"issue":"2","key":"ref3","first-page":"67","article-title":"A crowd counting network based on multi-scale pyramid transformer","volume":"19","author":"Zhang","year":"2024","journal-title":"CAAI Trans. Intell. Syst."},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3241175"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-04499-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3291824"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2837153"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1117\/1.JEI.31.4.041214"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2934989"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01730"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110513"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01492"},{"key":"ref13","article-title":"CounTR: Transformer-based generalised visual counting","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Chang"},{"key":"ref14","article-title":"Learning to count anything: Reference-less class-agnostic counting with weak supervision","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Hobley"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_5"},{"key":"ref16","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611789"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref20","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref21","article-title":"DAB-DETR: Dynamic anchor boxes are better queries for DETR","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.08.011"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-021-00877-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3013905"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3208714"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-022-03749-2"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3296571"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3277462"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3283289"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3135013"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00931"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00625"},{"key":"ref37","first-page":"313","article-title":"Scale-prior deformable convolution for exemplar-guided class-agnostic counting","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Lin"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref39","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref40","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.70"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.446"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3268226"},{"issue":"2","key":"ref44","first-page":"307","article-title":"Crowd counting method based on proportion fusion and multilayer scale-aware","volume":"19","author":"Meng","year":"2024","journal-title":"CAAI Trans. Intell. Syst."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tce.2024.3378166"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00091"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00283"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102537"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00039"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10740342.pdf?arnumber=10740342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:43Z","timestamp":1767638443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10740342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":49,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3488721","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}