{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T21:21:11Z","timestamp":1774041671766,"version":"3.50.1"},"reference-count":41,"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\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BE2023008-2"],"award-info":[{"award-number":["BE2023008-2"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371235"],"award-info":[{"award-number":["62371235"]}],"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":["U25A20444"],"award-info":[{"award-number":["U25A20444"]}],"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.2026.104773","type":"journal-article","created":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T16:53:19Z","timestamp":1773075199000},"page":"104773","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Diving into the Details: Holistic and partial feature fusion network for few-shot object counting"],"prefix":"10.1016","volume":"117","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8968-5783","authenticated-orcid":false,"given":"Wenjun","family":"Wu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1023-1286","authenticated-orcid":false,"given":"Shidong","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4039-7618","authenticated-orcid":false,"given":"Haofeng","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104773_b1","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.2026.104773_b2","doi-asserted-by":"crossref","unstructured":"M. Guo, L. Yuan, Z. Yan, B. Chen, Y. Wang, Q. Ye, Regressor-segmenter mutual prompt learning for crowd counting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 28380\u201328389.","DOI":"10.1109\/CVPR52733.2024.02681"},{"key":"10.1016\/j.jvcir.2026.104773_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.2026.104773_b4","doi-asserted-by":"crossref","unstructured":"C. Arteta, V. Lempitsky, A. Zisserman, Counting in the wild, in: Proceedings of the European Conference on Computer Vision, 2016, pp. 483\u2013498.","DOI":"10.1007\/978-3-319-46478-7_30"},{"key":"10.1016\/j.jvcir.2026.104773_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.compag.2019.05.049","article-title":"Automated pig counting using deep learning","author":"Tian","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"10.1016\/j.jvcir.2026.104773_b6","doi-asserted-by":"crossref","unstructured":"E. Lu, W. Xie, A. Zisserman, Class-agnostic counting, in: Proceedings of the Asian Conference on Computer Vision, 2019, pp. 669\u2013684.","DOI":"10.1007\/978-3-030-20893-6_42"},{"key":"10.1016\/j.jvcir.2026.104773_b7","doi-asserted-by":"crossref","unstructured":"V. Ranjan, U. Sharma, T. Nguyen, M. Hoai, Learning to count everything, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3394\u20133403.","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"10.1016\/j.jvcir.2026.104773_b8","doi-asserted-by":"crossref","unstructured":"N. \u0110uki\u0107, A. Luke\u017ei\u010d, V. Zavrtanik, M. Kristan, A low-shot object counting network with iterative prototype adaptation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 18872\u201318881.","DOI":"10.1109\/ICCV51070.2023.01730"},{"key":"10.1016\/j.jvcir.2026.104773_b9","doi-asserted-by":"crossref","unstructured":"J. Pelhan, V. Zavrtanik, M. Kristan, et al., DAVE-A Detect-and-Verify Paradigm for Low-Shot Counting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 23293\u201323302.","DOI":"10.1109\/CVPR52733.2024.02198"},{"key":"10.1016\/j.jvcir.2026.104773_b10","unstructured":"L. Chang, Z. Yujie, Z. Andrew, X. Weidi, CounTR: Transformer-based Generalised Visual Counting, in: Proceedings of the British Machine Vision Conference, 2022, pp. 1\u201310."},{"key":"10.1016\/j.jvcir.2026.104773_b11","doi-asserted-by":"crossref","unstructured":"Z. Wang, L. Xiao, Z. Cao, H. Lu, Vision transformer off-the-shelf: A surprising baseline for few-shot class-agnostic counting, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2024, pp. 5832\u20135840.","DOI":"10.1609\/aaai.v38i6.28396"},{"key":"10.1016\/j.jvcir.2026.104773_b12","doi-asserted-by":"crossref","unstructured":"K. He, X. Chen, S. Xie, Y. Li, P. Doll\u00e1r, R. Girshick, Masked autoencoders are scalable vision learners, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10.1016\/j.jvcir.2026.104773_b13","doi-asserted-by":"crossref","unstructured":"A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A.C. Berg, W.-Y. Lo, et al., Segment anything, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 4015\u20134026.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"10.1016\/j.jvcir.2026.104773_b14","doi-asserted-by":"crossref","unstructured":"D. Liang, J. Xie, Z. Zou, X. Ye, W. Xu, X. Bai, CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 2893\u20132903.","DOI":"10.1109\/CVPR52729.2023.00283"},{"key":"10.1016\/j.jvcir.2026.104773_b15","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.2026.104773_b16","doi-asserted-by":"crossref","unstructured":"W. Lin, A.B. Chan, Optimal Transport Minimization: Crowd Localization on Density Maps for Semi-Supervised Counting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 21663\u201321673.","DOI":"10.1109\/CVPR52729.2023.02075"},{"key":"10.1016\/j.jvcir.2026.104773_b17","doi-asserted-by":"crossref","unstructured":"Z. Du, J. Deng, M. Shi, Domain-general crowd counting in unseen scenarios, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2023, pp. 561\u2013570.","DOI":"10.1609\/aaai.v37i1.25131"},{"key":"10.1016\/j.jvcir.2026.104773_b18","doi-asserted-by":"crossref","unstructured":"M.-R. Hsieh, Y.-L. Lin, W.H. Hsu, Drone-based object counting by spatially regularized regional proposal network, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2017, pp. 4145\u20134153.","DOI":"10.1109\/ICCV.2017.446"},{"key":"10.1016\/j.jvcir.2026.104773_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2025.104560","article-title":"MP-YOLO: multidimensional feature fusion based layer adaptive pruning YOLO for dense vehicle object detection algorithm","volume":"112","author":"Zhou","year":"2025","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104773_b20","doi-asserted-by":"crossref","unstructured":"P. Thanasutives, K.-i. Fukui, M. Numao, B. Kijsirikul, Encoder-decoder based convolutional neural networks with multi-scale-aware modules for crowd counting, in: Proceedings of the International Conference on Pattern Recognition, ICPR, 2021, pp. 2382\u20132389.","DOI":"10.1109\/ICPR48806.2021.9413286"},{"key":"10.1016\/j.jvcir.2026.104773_b21","doi-asserted-by":"crossref","unstructured":"Y. Miao, Z. Lin, G. Ding, J. Han, Shallow feature based dense attention network for crowd counting, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2020, pp. 11765\u201311772.","DOI":"10.1609\/aaai.v34i07.6848"},{"key":"10.1016\/j.jvcir.2026.104773_b22","doi-asserted-by":"crossref","unstructured":"X. Jiang, L. Zhang, M. Xu, T. Zhang, P. Lv, B. Zhou, X. Yang, Y. Pang, Attention scaling for crowd counting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 4706\u20134715.","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"10.1016\/j.jvcir.2026.104773_b23","doi-asserted-by":"crossref","unstructured":"H. Lin, Z. Ma, R. Ji, Y. Wang, X. Hong, Boosting crowd counting via multifaceted attention, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19628\u201319637.","DOI":"10.1109\/CVPR52688.2022.01901"},{"key":"10.1016\/j.jvcir.2026.104773_b24","doi-asserted-by":"crossref","unstructured":"C. Liu, H. Lu, Z. Cao, T. Liu, Point-query quadtree for crowd counting, localization, and more, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 1676\u20131685.","DOI":"10.1109\/ICCV51070.2023.00161"},{"key":"10.1016\/j.jvcir.2026.104773_b25","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"428","article-title":"Improving point-based crowd counting and localization based on auxiliary point guidance","author":"Chen","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104773_b26","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3400310","article-title":"Crowd counting and individual localization using pseudo square label","author":"Ryu","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvcir.2026.104773_b27","unstructured":"Y. Xu, F. Song, H. Zhang, Learning Spatial Similarity Distribution for Few-shot Object Counting, in: Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024, pp. 1057\u20131515."},{"key":"10.1016\/j.jvcir.2026.104773_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105632","article-title":"CREAM: Few-shot object counting with cross refinement and adaptive density map","author":"Xu","year":"2025","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.jvcir.2026.104773_b29","article-title":"Counting with ease: Class-agnostic counting via one-shot detection across diverse domains","author":"Peng","year":"2025","journal-title":"Neural Netw."},{"key":"10.1016\/j.jvcir.2026.104773_b30","doi-asserted-by":"crossref","unstructured":"Z. You, K. Yang, W. Luo, X. Lu, L. Cui, X. Le, Few-Shot Object Counting With Similarity-Aware Feature Enhancement, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 6315\u20136324.","DOI":"10.1109\/WACV56688.2023.00625"},{"key":"10.1016\/j.jvcir.2026.104773_b31","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.jvcir.2026.104773_b32","doi-asserted-by":"crossref","unstructured":"N. Amini-Naieni, T. Han, A. Zisserman, CountGD: Multi-Modal Open-World Counting, in: Proceedings of the International Conference on Neural Information Processing Systems, 2024, pp. 48810\u201348837.","DOI":"10.52202\/079017-1547"},{"key":"10.1016\/j.jvcir.2026.104773_b33","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104773_b34","doi-asserted-by":"crossref","unstructured":"S.-D. Yang, H.-T. Su, W.H. Hsu, W.-C. Chen, Class-agnostic few-shot object counting, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2021, pp. 870\u2013878.","DOI":"10.1109\/WACV48630.2021.00091"},{"key":"10.1016\/j.jvcir.2026.104773_b35","series-title":"Object counting: You only need to look at one","author":"Lin","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104773_b36","doi-asserted-by":"crossref","unstructured":"M. Shi, H. Lu, C. Feng, C. Liu, Z. Cao, Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 9529\u20139538.","DOI":"10.1109\/CVPR52688.2022.00931"},{"key":"10.1016\/j.jvcir.2026.104773_b37","doi-asserted-by":"crossref","unstructured":"V. Ranjan, M. Hoai, Vicinal counting networks, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4221\u20134230.","DOI":"10.1109\/CVPRW56347.2022.00467"},{"key":"10.1016\/j.jvcir.2026.104773_b38","unstructured":"W. Lin, K. Yang, X. Ma, J. Gao, L. Liu, S. Liu, J. Hou, S. Yi, A. Chan, Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting, in: Proceedings of the British Machine Vision Conference, 2022, pp. 1\u201310."},{"key":"10.1016\/j.jvcir.2026.104773_b39","doi-asserted-by":"crossref","unstructured":"Z. Huang, M. Dai, Y. Zhang, J. Zhang, H. Shan, Point, Segment and Count: A Generalized Framework for Object Counting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 17067\u201317076.","DOI":"10.1109\/CVPR52733.2024.01615"},{"key":"10.1016\/j.jvcir.2026.104773_b40","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 Netw."},{"key":"10.1016\/j.jvcir.2026.104773_b41","doi-asserted-by":"crossref","unstructured":"S. Gong, S. Zhang, J. Yang, D. Dai, B. Schiele, Class-agnostic object counting robust to intraclass diversity, in: European Conference on Computer Vision, 2022, pp. 388\u2013403.","DOI":"10.1007\/978-3-031-19827-4_23"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000684?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326000684?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T19:32:10Z","timestamp":1774035130000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326000684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":41,"alternative-id":["S1047320326000684"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104773","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":"Diving into the Details: Holistic and partial feature fusion network for few-shot object counting","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.2026.104773","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":"104773"}}