{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T01:42:19Z","timestamp":1776130939727,"version":"3.50.1"},"reference-count":59,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036005"],"award-info":[{"award-number":["62036005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.jvcir.2026.104793","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:57:07Z","timestamp":1774630627000},"page":"104793","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["HierarchicalGeoCount: Hierarchical scale perception for zero-shot object counting in remote sensing"],"prefix":"10.1016","volume":"117","author":[{"given":"Binyuan","family":"Huang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5420-6308","authenticated-orcid":false,"given":"Jiayi","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6854-4053","authenticated-orcid":false,"given":"Zhenzhong","family":"Chen","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104793_b1","doi-asserted-by":"crossref","unstructured":"Ruixiang Jiang, Lingbo Liu, Changwen Chen, CLIP-Count: Towards text-guided zero-shot object counting, in: Proc. 31st ACM Int. Conf. Multimedia, 2023, pp. 4535\u20134545.","DOI":"10.1145\/3581783.3611789"},{"key":"10.1016\/j.jvcir.2026.104793_b2","doi-asserted-by":"crossref","unstructured":"Yuhao Lin, Haiming Xu, Lingqiao Liu, Javen Qinfeng Shi, A simple-but-effective baseline for training-free class-agnostic counting, in: Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis., 2025, pp. 8155\u20138164.","DOI":"10.1109\/WACV61041.2025.00791"},{"key":"10.1016\/j.jvcir.2026.104793_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2024.104323","article-title":"Crowd counting network based on attention feature fusion and multi-column feature enhancement","volume":"105","author":"Liu","year":"2024","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104793_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2023.103853","article-title":"CrowdFormer: Weakly-supervised crowd counting with improved generalizability","volume":"94","author":"Savner","year":"2023","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104793_b5","unstructured":"Zenglin Shi, Ying Sun, Mengmi Zhang, Training-free object counting with prompts, in: Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis., 2024, pp. 323\u2013331."},{"key":"10.1016\/j.jvcir.2026.104793_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2025.104387","article-title":"Learning scalable Omni-scale distribution for crowd counting","volume":"107","author":"Wang","year":"2025","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104793_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2024.104078","article-title":"Correlation-attention guided regression network for efficient crowd counting","volume":"99","author":"Zeng","year":"2024","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104793_b8","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.jvcir.2019.05.003","article-title":"An object counting network based on hierarchical context and feature fusion","volume":"62","author":"Zhang","year":"2019","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104793_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2022.116555","article-title":"Counting and locating high-density objects using convolutional neural network","volume":"195","author":"de Arruda","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.jvcir.2026.104793_b10","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2022.3153946","article-title":"PSGCNet: A pyramidal scale and global context guided network for dense object counting in remote-sensing images","volume":"60","author":"Gao","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104793_b11","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2024.104608","article-title":"SCU-counting: A large-scale benchmark dataset for multi-class object counting","volume":"163","author":"Wei","year":"2024","journal-title":"Transp. Res. Part C: Emerg. Technol."},{"key":"10.1016\/j.jvcir.2026.104793_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102537","article-title":"Towards zero-shot object counting via deep spatial prior cross-modality fusion","volume":"111","author":"Chen","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.jvcir.2026.104793_b13","unstructured":"Yuxuan Li, Qibin Hou, Zhaohui Zheng, Ming-Ming Cheng, Jian Yang, Xiang Li, Large Selective Kernel Network for Remote Sensing Object Detection, in: Proc. IEEE\/CVF Int. Conf. Comput. Vis., 2023, pp. 16794\u201316805."},{"key":"10.1016\/j.jvcir.2026.104793_b14","article-title":"Distantly supervised reinforcement localization for real-world object distribution estimation","author":"Guo","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.jvcir.2026.104793_b15","doi-asserted-by":"crossref","unstructured":"Jianghang Lin, Yunhang Shen, Bingquan Wang, Shaohui Lin, Ke Li, Liujuan Cao, Weakly supervised open-vocabulary object detection, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 38, 2024, pp. 3404\u20133412.","DOI":"10.1609\/aaai.v38i4.28127"},{"key":"10.1016\/j.jvcir.2026.104793_b16","doi-asserted-by":"crossref","unstructured":"Seunggu Kang, WonJun Moon, Euiyeon Kim, Jae-Pil Heo, VLCounter: Text-aware visual representation for zero-shot object counting, in: Proc. AAAI Conf. Artif. Intell., Vol. 38, 2024, pp. 2714\u20132722.","DOI":"10.1609\/aaai.v38i3.28050"},{"key":"10.1016\/j.jvcir.2026.104793_b17","doi-asserted-by":"crossref","unstructured":"Shenghao Fu, Qize Yang, Qijie Mo, Junkai Yan, Xihan Wei, Jingke Meng, Xiaohua Xie, Wei-Shi Zheng, Llmdet: Learning strong open-vocabulary object detectors under the supervision of large language models, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 14987\u201314997.","DOI":"10.1109\/CVPR52734.2025.01396"},{"key":"10.1016\/j.jvcir.2026.104793_b18","unstructured":"Reza Bahmanyar, Eleonora Vig, Peter Reinartz, MRCNet: Crowd counting and density map estimation in aerial and ground imagery, in: BMVC\u2019s Workshop on Object Detection and Recognition for Security Screenin, BMVC-ODRSS, 2019, pp. 1\u201312."},{"key":"10.1016\/j.jvcir.2026.104793_b19","unstructured":"Longyin Wen, et al., Detection, tracking, and counting meets drones in crowds: A benchmark, in: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., 2021, pp. 7812\u20137821."},{"key":"10.1016\/j.jvcir.2026.104793_b20","series-title":"2019 IEEE Symp. Comput. Commun.","first-page":"1","article-title":"Counting vehicles with deep learning in onboard UAV imagery","author":"Amato","year":"2019"},{"key":"10.1016\/j.jvcir.2026.104793_b21","doi-asserted-by":"crossref","unstructured":"Jingxian Huang, et al., Drone-Based Car Counting via Density Map Learning, in: Proc. 2020 IEEE Int. Conf. Vis. Commun. Image Process., 2020, pp. 239\u2013242.","DOI":"10.1109\/VCIP49819.2020.9301785"},{"key":"10.1016\/j.jvcir.2026.104793_b22","doi-asserted-by":"crossref","DOI":"10.1109\/TGRS.2023.3295802","article-title":"TreeFormer: a semi-supervised transformer-based framework for tree counting from a single high resolution image","author":"Amirkolaee","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104793_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecolind.2021.107591","article-title":"Tree counting with high spatial-resolution satellite imagery based on deep neural networks","volume":"125","author":"Yao","year":"2021","journal-title":"Ecol. Indic."},{"issue":"12","key":"10.1016\/j.jvcir.2026.104793_b24","doi-asserted-by":"crossref","first-page":"2605","DOI":"10.1016\/j.joule.2018.11.021","article-title":"DeepSolar: A machine learning framework to efficiently construct a solar deployment database in the United States","volume":"2","author":"Yu","year":"2018","journal-title":"Joule"},{"key":"10.1016\/j.jvcir.2026.104793_b25","series-title":"2017 IEEE Int. Geosci. Remote Sens. Symp.","first-page":"874","article-title":"A deep convolutional neural network, with pre-training, for solar photovoltaic array detection in aerial imagery","author":"Malof","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104793_b26","first-page":"1","article-title":"NWPU-MOC: a benchmark for fine-grained multicategory object counting in aerial images","volume":"62","author":"Gao","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104793_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131310","article-title":"A generic class-agnostic object counting network with adaptive offset deformable convolution","volume":"654","author":"Wu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.jvcir.2026.104793_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130997","article-title":"Beyond decoders: Learning prompt-aware features for few-shot object counting","volume":"651","author":"Zhao","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.jvcir.2026.104793_b29","article-title":"Feature enhancement network for object detection in optical remote sensing images","author":"Cheng","year":"2021","journal-title":"J. Remote. Sens."},{"key":"10.1016\/j.jvcir.2026.104793_b30","first-page":"1","article-title":"Anchor-free oriented proposal generator for object detection","volume":"60","author":"Cheng","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104793_b31","series-title":"Proc. Eur. Conf. Comput. Vis., Amsterdam, the Netherlands, 2016","first-page":"785","article-title":"A large contextual dataset for classification, detection and counting of cars with deep learning","volume":"Vol. 14","author":"Mundhenk","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104793_b32","doi-asserted-by":"crossref","unstructured":"Yuan Qiang Cai, et al., Guided attention network for object detection and counting on drones, in: Proc. 28th ACM Int. Conf. Multimedia, 2020, pp. 709\u2013717.","DOI":"10.1145\/3394171.3413816"},{"key":"10.1016\/j.jvcir.2026.104793_b33","doi-asserted-by":"crossref","unstructured":"Meng-Ru Hsieh, Yen-Liang Lin, Winston H. Hsu, Drone-based object counting by spatially regularized regional proposal network, in: Proc. IEEE Int. Conf. Comput. Vis., 2017, pp. 4145\u20134153.","DOI":"10.1109\/ICCV.2017.446"},{"issue":"5","key":"10.1016\/j.jvcir.2026.104793_b34","doi-asserted-by":"crossref","first-page":"3642","DOI":"10.1109\/TGRS.2020.3020555","article-title":"Counting from sky: A large-scale data set for remote sensing object counting and a benchmark method","volume":"59","author":"Gao","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104793_b35","doi-asserted-by":"crossref","first-page":"1570","DOI":"10.1109\/LSP.2021.3096119","article-title":"Dilated-scale-aware category-attention convnet for multi-class object counting","volume":"28","author":"Xu","year":"2021","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.jvcir.2026.104793_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.105449","article-title":"A benchmark for multi-class object counting and size estimation using deep convolutional neural networks","volume":"116","author":"Liu","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.jvcir.2026.104793_b37","series-title":"LMCNet: A lightweight multi-class counting network with ghost attention mechanism and focal-L2 loss","author":"Zhang","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104793_b38","first-page":"1","article-title":"Balanced density regression network for remote sensing object counting","volume":"62","author":"Guo","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104793_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131135","article-title":"PolaCount: Text-specified zero-shot object counting with pyramid polarity-aware cross-attention","volume":"652","author":"Qian","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.jvcir.2026.104793_b40","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130759","article-title":"TPSC:Text-guided parameter-efficient fine-tuning segmentation for object counting","volume":"649","author":"Shi","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.jvcir.2026.104793_b41","doi-asserted-by":"crossref","unstructured":"Liunian Harold Li, Pengchuan Zhang, Haotian Zhang, Jianwei Yang, Chunyuan Li, Yiwu Zhong, Lijuan Wang, Lu Yuan, Lei Zhang, Jenq-Neng Hwang, et al., Grounded language-image pre-training, in: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., 2022, pp. 10965\u201310975.","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"10.1016\/j.jvcir.2026.104793_b42","series-title":"Adv. Neural Inf. Process. Syst.","article-title":"Scaling open-vocabulary object detection","volume":"Vol. 36","author":"Minderer","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104793_b43","series-title":"Proc. Eur. Conf. Comput. Vis.","first-page":"38","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","author":"Liu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104793_b44","doi-asserted-by":"crossref","unstructured":"Qing Jiang, Feng Li, Zhaoyang Zeng, Tianhe Ren, Shilong Liu, Lei Zhang, T-Rex2: Towards generic object detection via text-visual prompt synergy, in: Proc. Eur. Conf. Comput. Vis., 2024, pp. 1\u201316.","DOI":"10.1109\/TPAMI.2026.3672908"},{"key":"10.1016\/j.jvcir.2026.104793_b45","doi-asserted-by":"crossref","unstructured":"Fatih Cagatay Akyon, Sinan Onur Altinuc, Alptekin Temizel, Slicing aided hyper inference and fine-tuning for small object detection, in: IEEE Int. Conf. Image Process., 2022, pp. 966\u2013970.","DOI":"10.1109\/ICIP46576.2022.9897990"},{"key":"10.1016\/j.jvcir.2026.104793_b46","series-title":"Remote sensing semantic segmentation quality assessment based on vision language model","author":"Shi","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104793_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111409","article-title":"A closer look at the explainability of contrastive language-image pre-training","volume":"162","author":"Li","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.jvcir.2026.104793_b48","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res. J."},{"key":"10.1016\/j.jvcir.2026.104793_b49","doi-asserted-by":"crossref","unstructured":"Yingying Zhang, Desen Zhou, Siqin Chen, Shenghua Gao, Yi Ma, Single-image crowd counting via multi-column convolutional neural network, in: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 589\u2013597.","DOI":"10.1109\/CVPR.2016.70"},{"key":"10.1016\/j.jvcir.2026.104793_b50","doi-asserted-by":"crossref","unstructured":"Yuhong Li, Xiaofan Zhang, Deming Chen, CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes, in: Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 1091\u20131100.","DOI":"10.1109\/CVPR.2018.00120"},{"key":"10.1016\/j.jvcir.2026.104793_b51","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neucom.2019.08.018","article-title":"SCAR: Spatial-\/channel-wise attention regression networks for crowd counting","volume":"363","author":"Gao","year":"2019","journal-title":"Neurocomputing"},{"key":"10.1016\/j.jvcir.2026.104793_b52","doi-asserted-by":"crossref","unstructured":"Qi Wang, Junyu Gao, Wei Lin, Yuan Yuan, Learning from synthetic data for crowd counting in the wild, in: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., 2019, pp. 8198\u20138207.","DOI":"10.1109\/CVPR.2019.00839"},{"issue":"16","key":"10.1016\/j.jvcir.2026.104793_b53","doi-asserted-by":"crossref","first-page":"4026","DOI":"10.3390\/rs14164026","article-title":"Global multi-scale information fusion for multi-class object counting in remote sensing images","volume":"14","author":"Gao","year":"2022","journal-title":"Remote. Sens."},{"key":"10.1016\/j.jvcir.2026.104793_b54","doi-asserted-by":"crossref","unstructured":"Siyang Dai, Jun Liu, Ngai-Man Cheung, Referring expression counting, in: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., 2024, pp. 16985\u201316995.","DOI":"10.1109\/CVPR52733.2024.01607"},{"key":"10.1016\/j.jvcir.2026.104793_b55","doi-asserted-by":"crossref","unstructured":"Xinkun Cao, Zhipeng Wang, Yanyun Zhao, Fei Su, Scale aggregation network for accurate and efficient crowd counting, in: Proc. Eur. Conf. Comput. Vis., 2018, pp. 734\u2013750.","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"10.1016\/j.jvcir.2026.104793_b56","doi-asserted-by":"crossref","unstructured":"Vishwanath A. Sindagi, Vishal M. Patel, CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting, in: Proc. 14th IEEE Int. Conf. Adv. Video Signal-Based Surveillance, 2017, pp. 1\u20136.","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"10.1016\/j.jvcir.2026.104793_b57","unstructured":"Weizhe Liu, Mathieu Salzmann, Pascal Fua, Context-aware crowd counting, in: Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit., 2019, pp. 5099\u20135108."},{"key":"10.1016\/j.jvcir.2026.104793_b58","doi-asserted-by":"crossref","unstructured":"Xinya Chen, Yanrui Bin, Nong Sang, Changxin Gao, Scale pyramid network for crowd counting, in: Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis., 2019, pp. 1941\u20131950.","DOI":"10.1109\/WACV.2019.00211"},{"key":"10.1016\/j.jvcir.2026.104793_b59","unstructured":"Zhiheng Ma, Xing Wei, Xiaopeng Hong, Yihong Gong, Bayesian loss for crowd count estimation with point supervision, in: Proc. IEEE\/CVF Int. Conf. Comput. Vis., 2019, pp. 6142\u20136151."}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S104732032600088X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S104732032600088X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T00:45:20Z","timestamp":1776127520000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S104732032600088X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":59,"alternative-id":["S104732032600088X"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104793","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"HierarchicalGeoCount: Hierarchical scale perception for zero-shot object counting in remote sensing","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104793","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104793"}}