{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:40:07Z","timestamp":1767206407131,"version":"build-2238731810"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T00:00:00Z","timestamp":1680134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Given some exemplars, few-shot object counting aims to count the corresponding class objects in query images. However, when there are many target objects or background interference in the query image, some target objects may have occlusion and overlap, which causes a decrease in counting accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>To overcome the problem, we propose a novel Hough matching feature enhancement network. First, we extract the image feature with a fixed convolutional network and refine it through local self-attention. And we design an exemplar feature aggregation module to enhance the commonality of the exemplar feature. Then, we build a Hough space to vote for candidate object regions. The Hough matching outputs reliable similarity maps between exemplars and the query image. Finally, we augment the query feature with exemplar features according to the similarity maps, and we use a cascade structure to further enhance the query feature.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experiment results on FSC-147 show that our network performs best compared to the existing methods, and the mean absolute counting error on the test set improves from 14.32 to 12.74.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>Ablation experiments demonstrate that Hough matching helps to achieve more accurate counting compared with previous matching methods.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fncom.2023.1145219","type":"journal-article","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T07:41:51Z","timestamp":1680162111000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Accurate few-shot object counting with Hough matching feature enhancement"],"prefix":"10.3389","volume":"17","author":[{"given":"Zhiquan","family":"He","sequence":"first","affiliation":[]},{"given":"Donghong","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Hengyou","family":"Wang","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,3,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1016\/j.ygeno.2019.09.006","article-title":"Pred-bvp-unb: fast prediction of bacteriophage virion proteins using un-biased multi-perspective properties with recursive feature elimination","volume":"112","author":"Arif","year":"2020","journal-title":"Genomics"},{"key":"B2","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.jtbi.2018.01.008","article-title":"imem-2lsaac: a two-level model for discrimination of membrane proteins and their types by extending the notion of saac into chou's pseudo amino acid composition","volume":"442","author":"Arif","year":"2018","journal-title":"J. Theor. Biol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2749","DOI":"10.1109\/TCBB.2021.3102133","article-title":"Deepcppred: a deep learning framework for the discrimination of cell-penetrating peptides and their uptake efficiencies","volume":"19","author":"Arif","year":"2021","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinform"},{"key":"B4","first-page":"483","article-title":"\u201cCounting in the wild,\u201d","author":"Arteta","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"B5","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/0031-3203(81)90009-1","article-title":"Generalizing the Hough transform to detect arbitrary shapes","volume":"13","author":"Ballard","year":"1981","journal-title":"Patt. Recogn."},{"key":"B6","first-page":"1201","article-title":"\u201cUnsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals,\u201d","author":"Cho","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B7","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","article-title":"\u201cImagenet: A large-scale hierarchical image database,\u201d","author":"Deng","year":"2009","journal-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B8","first-page":"6569","article-title":"\u201cCenternet: keypoint triplets for object detection,\u201d","author":"Duan","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"B9","first-page":"4013","article-title":"\u201cFew-shot object detection with attention-rpn and multi-relation detector,\u201d","author":"Fan","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B10","first-page":"1126","article-title":"\u201cModel-agnostic meta-learning for fast adaptation of deep networks,\u201d","author":"Finn","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"B11","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/978-1-4471-4929-3_11","article-title":"\u201cClass-specific hough forests for object detection,\u201d","author":"Gall","year":"2013","journal-title":"Decision Forests for Computer Vision and Medical Image Analysis"},{"key":"B12","doi-asserted-by":"publisher","first-page":"38","DOI":"10.2174\/1386207323666201204140438","article-title":"Targetmm: accurate missense mutation prediction by utilizing local and global sequence information with classifier ensemble","volume":"25","author":"Ge","year":"","journal-title":"Combinat. Chem. High Throughput Screening"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab530","article-title":"Prediction of disease-associated nssnps by integrating multi-scale resnet models with deep feature fusion","author":"Ge","year":"","journal-title":"Brief. Bioinform"},{"key":"B14","doi-asserted-by":"publisher","first-page":"6400","DOI":"10.1016\/j.csbj.2021.11.024","article-title":"Muttmpredictor: robust and accurate cascade xgboost classifier for prediction of mutations in transmembrane proteins","volume":"19","author":"Ge","year":"2021","journal-title":"Comput. Struct. Biotechnol. J"},{"key":"B15","first-page":"5227","article-title":"\u201cPrecise detection in densely packed scenes,\u201d","author":"Goldman","year":"2019","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B16","first-page":"1831","article-title":"\u201cScnet: learning semantic correspondence,\u201d","author":"Han","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"B17","first-page":"770","article-title":"\u201cDeep residual learning for image recognition,\u201d","author":"He","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B18","author":"Hough","year":"1962","journal-title":"Method and means for recognizing complex patterns"},{"key":"B19","first-page":"4145","article-title":"\u201cDrone-based object counting by spatially regularized regional proposal network,\u201d","author":"Hsieh","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"B20","first-page":"4706","article-title":"\u201cAttention scaling for crowd counting,\u201d","author":"Jiang","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B21","first-page":"8420","article-title":"\u201cFew-shot object detection via feature reweighting,\u201d","author":"Kang","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"B22","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1007\/978-3-319-46487-9_13","article-title":"\u201cDeep learning of local rgb-d patches for 3d object detection and 6d pose estimation,\u201d","author":"Kehl","year":"2016","journal-title":"Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"B24","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1109\/3DIMPVT.2011.30","article-title":"\u201cScene cut: class-specific object detection and segmentation in 3D scenes,\u201d","author":"Knopp","year":"2011","journal-title":"2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission"},{"key":"B25","first-page":"2980","article-title":"\u201cFocal loss for dense object detection,\u201d","author":"Lin","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"B26","first-page":"4823","article-title":"\u201cCross-modal collaborative representation learning and a large-scale rgbt benchmark for crowd counting,\u201d","author":"Liu","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B27","first-page":"669","article-title":"\u201cClass-agnostic counting,\u201d","author":"Lu","year":"2018","journal-title":"Asian Conference on Computer Vision"},{"key":"B28","first-page":"6142","article-title":"\u201cBayesian loss for crowd count estimation with point supervision,\u201d","author":"Ma","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"B29","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.cviu.2017.04.002","article-title":"Hough-cnn: deep learning for segmentation of deep brain regions in mri and ultrasound","volume":"164","author":"Milletari","year":"2017","journal-title":"Comput. Vis. Image Understand"},{"key":"B30","first-page":"3395","article-title":"\u201cHyperpixel flow: semantic correspondence with multi-layer neural features,\u201d","author":"Min","year":"2019","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"B31","first-page":"346","article-title":"\u201cLearning to compose hypercolumns for visual correspondence,\u201d","author":"Min","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"B32","first-page":"785","article-title":"\u201cA large contextual dataset for classification, detection and counting of cars with deep learning,\u201d","author":"Mundhenk","year":"2016","journal-title":"European Conference on Computer Vision"},{"key":"B33","article-title":"\u201cStand-alone self-attention in vision models,\u201d","author":"Ramachandran","year":"2019","journal-title":"Advances in Neural Information Processing Systems Vol. 32"},{"key":"B34","first-page":"3394","article-title":"\u201cLearning to count everything,\u201d","author":"Ranjan","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B35","first-page":"779","article-title":"\u201cYou only look once: unified, real-time object detection,\u201d","author":"Redmon","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B36","article-title":"\u201cFaster R-CNN: towards real-time object detection with region proposal networks,\u201d","author":"Ren","year":"2015","journal-title":"Advances in Neural Information Processing Systems, Vol. 28"},{"key":"B37","first-page":"9529","article-title":"\u201cRepresent, compare, and learn: a similarity-aware framework for class-agnostic counting,\u201d","author":"Shi","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.3389\/fgene.2022.851688","article-title":"Identification of the ubiquitin-proteasome pathway domain by hyperparameter optimization based on a 2D convolutional neural network","author":"Sikander","year":"2022","journal-title":"Front. Genet"},{"key":"B39","first-page":"3365","article-title":"\u201cRethinking counting and localization in crowds: a purely point-based framework,\u201d","author":"Song","year":"2021","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1035","DOI":"10.1109\/TIP.2018.2875353","article-title":"Divide and count: generic object counting by image divisions","volume":"28","author":"Stahl","year":"2018","journal-title":"IEEE Trans. Image Process"},{"key":"B41","first-page":"12894","article-title":"\u201cScaling local self-attention for parameter efficient visual backbones,\u201d","author":"Vaswani","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B42","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1007\/978-3-319-46604-0_20","article-title":"\u201cCell counting by regression using convolutional neural network,\u201d","volume-title":"Computer Vision-ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part I 14","author":"Xue","year":"2016"},{"key":"B43","first-page":"870","article-title":"\u201cClass-agnostic few-shot object counting.,\u201d","author":"Yang","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision"},{"key":"B44","first-page":"6315","article-title":"\u201cFew-shot object counting with similarity-aware feature enhancement,\u201d","author":"You","year":"2023","journal-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision"},{"key":"B45","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/ICIP.2017.8296324","article-title":"\u201cMulti-scale convolutional neural networks for crowd counting,\u201d","author":"Zeng","year":"2017","journal-title":"2017 IEEE International Conference on Image Processing (ICIP)"},{"key":"B46","first-page":"557","article-title":"\u201cCross-view cross-scene multi-view crowd counting,\u201d","author":"Zhang","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"B47","first-page":"5898","article-title":"\u201cUnderstanding traffic density from large-scale web camera data,\u201d","author":"Zhang","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B48","first-page":"589","article-title":"\u201cSingle-image crowd counting via multi-column convolutional neural network,\u201d","author":"Zhang","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B49","first-page":"10076","article-title":"\u201cExploring self-attention for image recognition,\u201d","author":"Zhao","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"}],"updated-by":[{"DOI":"10.3389\/fncom.2023.1232762","type":"corrigendum","label":"Corrigendum","source":"publisher","updated":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T00:00:00Z","timestamp":1687219200000}}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2023.1145219\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T08:48:51Z","timestamp":1687250931000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2023.1145219\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,30]]},"references-count":49,"alternative-id":["10.3389\/fncom.2023.1145219"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2023.1145219","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,30]]},"article-number":"1145219"}}