{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T04:13:19Z","timestamp":1772856799851,"version":"3.50.1"},"reference-count":62,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"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-017"},{"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"},{"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-012"},{"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-004"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["24DP1501001"],"award-info":[{"award-number":["24DP1501001"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1016\/j.neunet.2025.107961","type":"journal-article","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T15:13:15Z","timestamp":1754579595000},"page":"107961","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Counting with ease: Class-agnostic counting via one-shot detection across diverse domains"],"prefix":"10.1016","volume":"193","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5870-0101","authenticated-orcid":false,"given":"Zhongxing","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3130-6338","authenticated-orcid":false,"given":"Bohui","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1905-6269","authenticated-orcid":false,"given":"Shugong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107961_bib0001","series-title":"Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6-12, 2014, proceedings, part III 13","first-page":"504","article-title":"Interactive object counting","author":"Arteta","year":"2014"},{"key":"10.1016\/j.neunet.2025.107961_bib0002","series-title":"Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, the Netherlands, October 11\u201314, 2016, proceedings, part VII 14","first-page":"483","article-title":"Counting in the wild","author":"Arteta","year":"2016"},{"key":"10.1016\/j.neunet.2025.107961_bib0003","series-title":"Computer vision\u2013ECCV 2016 workshops: Amsterdam, the Netherlands, October 8-10 and 15-16, 2016, proceedings, part II 14","first-page":"850","article-title":"Fully-convolutional siamese networks for object tracking","author":"Bertinetto","year":"2016"},{"key":"10.1016\/j.neunet.2025.107961_bib0004","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"12247","article-title":"Adaptive image transformer for one-shot object detection","author":"Chen","year":"2021"},{"key":"10.1016\/j.neunet.2025.107961_bib0005","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S. et al. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929."},{"issue":"11","key":"10.1016\/j.neunet.2025.107961_bib0006","doi-asserted-by":"crossref","first-page":"1522","DOI":"10.3390\/e23111522","article-title":"Automatic detection and counting of blood cells in smear images using retinanet","volume":"23","author":"Dra\u0142us","year":"2021","journal-title":"Entropy"},{"key":"10.1016\/j.neunet.2025.107961_bib0007","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"18872","article-title":"A low-shot object counting network with iterative prototype adaptation","author":"\u00d0uki\u0107","year":"2023"},{"key":"10.1016\/j.neunet.2025.107961_bib0008","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","article-title":"The pascal visual object classes (voc) challenge","volume":"88","author":"Everingham","year":"2010","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.neunet.2025.107961_bib0009","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4013","article-title":"Few-shot object detection with attention-RPN and multi-relation detector","author":"Fan","year":"2020"},{"key":"10.1016\/j.neunet.2025.107961_bib0010","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.neucom.2020.04.092","article-title":"Oscd: A one-shot conditional object detection framework","volume":"425","author":"Fu","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.107961_bib0011","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"5356","article-title":"Lvis: A dataset for large vocabulary instance segmentation","author":"Gupta","year":"2019"},{"key":"10.1016\/j.neunet.2025.107961_bib0012","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"2961","article-title":"Mask r-cnn","author":"He","year":"2017"},{"key":"10.1016\/j.neunet.2025.107961_bib0013","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neunet.2025.107961_bib0014","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"4145","article-title":"Drone-based object counting by spatially regularized regional proposal network","author":"Hsieh","year":"2017"},{"key":"10.1016\/j.neunet.2025.107961_bib0015","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"4145","article-title":"Drone-based object counting by spatially regularized regional proposal network","author":"Hsieh","year":"2017"},{"key":"10.1016\/j.neunet.2025.107961_bib0016","first-page":"2721","article-title":"One-shot object detection with co-attention and co-excitation","volume":"32","author":"Hsieh","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107961_bib0017","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"10185","article-title":"Dense relation distillation with context-aware aggregation for few-shot object detection","author":"Hu","year":"2021"},{"key":"10.1016\/j.neunet.2025.107961_bib0018","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"10.1016\/j.neunet.2025.107961_bib0019","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"532","article-title":"Composition loss for counting, density map estimation and localization in dense crowds","author":"Idrees","year":"2018"},{"key":"10.1016\/j.neunet.2025.107961_bib0020","series-title":"European conference on computer vision","first-page":"709","article-title":"Visual prompt tuning","author":"Jia","year":"2022"},{"key":"10.1016\/j.neunet.2025.107961_bib0021","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"4535","article-title":"Clip-count: Towards text-guided zero-shot object counting","author":"Jiang","year":"2023"},{"key":"10.1016\/j.neunet.2025.107961_bib0022","first-page":"1","article-title":"An accurate car counting in aerial images based on convolutional neural networks","volume":"14","author":"Kilic","year":"2021","journal-title":"Journal of Ambient Intelligence and Humanized Computing"},{"key":"10.1016\/j.neunet.2025.107961_bib0023","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.Y. et al. (2023). Segment anything. arXiv preprint arXiv:2304.02643.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.neunet.2025.107961_bib0024","first-page":"1324","article-title":"Learning to count objects in images","volume":"23","author":"Lempitsky","year":"2010","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107961_bib0025","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"8971","article-title":"High performance visual tracking with siamese region proposal network","author":"Li","year":"2018"},{"key":"10.1016\/j.neunet.2025.107961_bib0026","series-title":"Medical image computing and computer assisted intervention\u2013MICCAI 2019: 22nd International conference, Shenzhen, China, October 13\u201317, 2019, proceedings, part I 22","first-page":"514","article-title":"Deep instance-level hard negative mining model for histopathology images","author":"Li","year":"2019"},{"key":"10.1016\/j.neunet.2025.107961_bib0027","series-title":"2021 Digital image computing: Techniques and applications (DICTA)","first-page":"1","article-title":"Deep adaptive few example learning for microscopy image cell counting","author":"Li","year":"2021"},{"key":"10.1016\/j.neunet.2025.107961_bib0028","series-title":"European conference on computer vision","first-page":"38","article-title":"An end-to-end transformer model for crowd localization","author":"Liang","year":"2022"},{"key":"10.1016\/j.neunet.2025.107961_bib0029","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"19628","article-title":"Boosting crowd counting via multifaceted attention","author":"Lin","year":"2022"},{"key":"10.1016\/j.neunet.2025.107961_bib0030","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"638","article-title":"Explore the power of synthetic data on few-shot object detection","author":"Lin","year":"2023"},{"key":"10.1016\/j.neunet.2025.107961_bib0031","series-title":"Computer vision\u2013ECCV 2014: 13th European conference, Zurich, Switzerland, September 6-12, 2014, proceedings, part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.neunet.2025.107961_bib0032","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"1676","article-title":"Point-query quadtree for crowd counting, localization, and more","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2025.107961_bib0033","unstructured":"Liu, C., Zhong, Y., Zisserman, A., & Xie, W. (2022a). Countr: Transformer-based generalised visual counting. arXiv preprint arXiv:2208.13721."},{"key":"10.1016\/j.neunet.2025.107961_bib0034","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4823","article-title":"Cross-modal collaborative representation learning and a large-scale rgbt benchmark for crowd counting","author":"Liu","year":"2021"},{"key":"10.1016\/j.neunet.2025.107961_bib0035","series-title":"European conference on computer vision","first-page":"38","article-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2025"},{"key":"10.1016\/j.neunet.2025.107961_bib0036","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.neucom.2022.04.106","article-title":"Crowd counting method via a dynamic-refined density map network","volume":"497","author":"Liu","year":"2022","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.107961_bib0037","unstructured":"Michaelis, C., Ustyuzhaninov, I., Bethge, M., & Ecker, A.S. (2018). One-shot instance segmentation. arXiv preprint arXiv:1811.11507."},{"key":"10.1016\/j.neunet.2025.107961_bib0038","series-title":"Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, the Netherlands, October 11-14, 2016, proceedings, part III 14","first-page":"785","article-title":"A large contextual dataset for classification, detection and counting of cars with deep learning","author":"Mundhenk","year":"2016"},{"key":"10.1016\/j.neunet.2025.107961_bib0039","series-title":"European conference on computer vision","first-page":"348","article-title":"Few-shot object counting and detection","author":"Nguyen","year":"2022"},{"key":"10.1016\/j.neunet.2025.107961_bib0040","series-title":"Computer vision\u2013ECCV 2016: 14th European conference, Amsterdam, the Netherlands, october 11\u201314, 2016, proceedings, part VII 14","first-page":"615","article-title":"Towards perspective-free object counting with deep learning","author":"Onoro-Rubio","year":"2016"},{"key":"10.1016\/j.neunet.2025.107961_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126627","article-title":"Comprehensive review on vehicle detection, classification and counting on highways","volume":"556","author":"Premaratne","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.107961_bib0042","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.neunet.2025.107961_bib0043","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3394","article-title":"Learning to count everything","author":"Ranjan","year":"2021"},{"key":"10.1016\/j.neunet.2025.107961_bib0044","first-page":"91","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107961_bib0045","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9529","article-title":"Represent, compare, and learn: A similarity-aware framework for class-agnostic counting","author":"Shi","year":"2022"},{"key":"10.1016\/j.neunet.2025.107961_bib0046","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3365","article-title":"Rethinking counting and localization in crowds: A purely point-based framework","author":"Song","year":"2021"},{"key":"10.1016\/j.neunet.2025.107961_bib0047","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2325","article-title":"End-to-end people detection in crowded scenes","author":"Stewart","year":"2016"},{"key":"10.1016\/j.neunet.2025.107961_bib0048","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7352","article-title":"Fsce: Few-shot object detection via contrastive proposal encoding","author":"Sun","year":"2021"},{"key":"10.1016\/j.neunet.2025.107961_bib0049","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23913","article-title":"DeGPR: Deep guided posterior regularization for multi-class cell detection and counting","author":"Tyagi","year":"2023"},{"key":"10.1016\/j.neunet.2025.107961_bib0050","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2025.107961_bib0051","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"1974","article-title":"A generalized loss function for crowd counting and localization","author":"Wan","year":"2021"},{"key":"10.1016\/j.neunet.2025.107961_bib0052","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"14408","article-title":"Internimage: Exploring large-scale vision foundation models with deformable convolutions","author":"Wang","year":"2023"},{"key":"10.1016\/j.neunet.2025.107961_bib0053","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"7794","article-title":"Non-local neural networks","author":"Wang","year":"2018"},{"key":"10.1016\/j.neunet.2025.107961_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106126","article-title":"Satcount: A scale-aware transformer-based class-agnostic counting framework","volume":"172","author":"Wang","year":"2024","journal-title":"Neural Networks"},{"issue":"3","key":"10.1016\/j.neunet.2025.107961_bib0055","first-page":"3090","article-title":"Few-shot object detection and viewpoint estimation for objects in the wild","volume":"45","author":"Xiao","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"10.1016\/j.neunet.2025.107961_bib0056","first-page":"3090","article-title":"Few-shot object detection and viewpoint estimation for objects in the wild","volume":"45","author":"Xiao","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"10.1016\/j.neunet.2025.107961_bib0057","first-page":"283","article-title":"Microscopy cell counting and detection with fully convolutional regression networks","volume":"6","author":"Xie","year":"2018","journal-title":"Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization"},{"key":"10.1016\/j.neunet.2025.107961_bib0058","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7591","article-title":"Balanced and hierarchical relation learning for one-shot object detection","author":"Yang","year":"2022"},{"key":"10.1016\/j.neunet.2025.107961_bib0059","unstructured":"Zhang, W., Xiao, X., Shan, H., & Liu, E. (2023). Adaptive base-class suppression and prior guidance network for one-shot object detection. arXiv preprint arXiv:2303.14240."},{"key":"10.1016\/j.neunet.2025.107961_bib0060","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"7601","article-title":"Semantic-aligned fusion transformer for one-shot object detection","author":"Zhao","year":"2022"},{"key":"10.1016\/j.neunet.2025.107961_bib0061","series-title":"European conference on computer vision","first-page":"368","article-title":"Zero-shot object counting with good exemplars","author":"Zhu","year":"2025"},{"key":"10.1016\/j.neunet.2025.107961_bib0062","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"9308","article-title":"Deformable convnets v2: More deformable, better results","author":"Zhu","year":"2019"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025008421?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025008421?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T15:19:57Z","timestamp":1772810397000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025008421"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":62,"alternative-id":["S0893608025008421"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107961","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Counting with ease: Class-agnostic counting via one-shot detection across diverse domains","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107961","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"107961"}}