{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T23:11:40Z","timestamp":1784761900358,"version":"3.55.0"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,5,29]],"date-time":"2021-05-29T00:00:00Z","timestamp":1622246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,29]],"date-time":"2021-05-29T00:00:00Z","timestamp":1622246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61773085"],"award-info":[{"award-number":["61773085"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s10489-021-02537-6","type":"journal-article","created":{"date-parts":[[2021,5,29]],"date-time":"2021-05-29T10:03:33Z","timestamp":1622282613000},"page":"1825-1837","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Pyramid-dilated deep convolutional neural network for crowd counting"],"prefix":"10.1007","volume":"52","author":[{"given":"Weixing","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanli","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,5,29]]},"reference":[{"key":"2537_CR1","unstructured":"Lempitsky V, Zisserman A (2010) Learning to count objects in images,\u201d Advances in Neural Information Processing Systems, pp. 1324\u20131332"},{"key":"2537_CR2","doi-asserted-by":"crossref","unstructured":"Boominathan L, Kruthiventi SS, Babu RV (2016) Crowdnet: a deep convolutional network for dense crowd counting,\u201d Proceedings of the 24th ACM International Conference on Multimedia, pp. 640\u2013644","DOI":"10.1145\/2964284.2967300"},{"key":"2537_CR3","doi-asserted-by":"crossref","unstructured":"Zhang Y, Zhou D, Chen S, Gao S, Ma Y (2016) Single-image crowd counting via multi-column convolutional neural network. IEEE Confer Comput VisionPattern Recogn:589\u2013597","DOI":"10.1109\/CVPR.2016.70"},{"key":"2537_CR4","doi-asserted-by":"crossref","unstructured":"Sam DB, Surya S, Babu RV (2017) Switching convolutional neural network for crowd counting,\u201d IEEE Conference on Computer Vision and Pattern Recognition, pp. 5744\u20135752","DOI":"10.1109\/CVPR.2017.429"},{"key":"2537_CR5","doi-asserted-by":"crossref","unstructured":"Sindagi VA, Patel VM (2017) Generating high-quality crowd density maps using contextual pyramid cnns,\u201d IEEE International Conference on Computer Vision (ICCV), pp. 1879-1888","DOI":"10.1109\/ICCV.2017.206"},{"key":"2537_CR6","doi-asserted-by":"crossref","unstructured":"Deb D, Ventura J (2018) An aggregated multicolumn dilated convolution network for perspective-free counting, 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 308\u2013317","DOI":"10.1109\/CVPRW.2018.00057"},{"key":"2537_CR7","doi-asserted-by":"crossref","unstructured":"Ji Q, Zhu T, Bao D (2020) A hybrid model of convolutional neural networks and deep regression forests for crowd counting,\u201d Applied Intelligence, pp. 1\u201315","DOI":"10.1007\/s10489-020-01688-2"},{"key":"2537_CR8","unstructured":"Duan H, Wang S, Guan Y (2020) SOFA-Net: Second-Order and First-order Attention Network for Crowd Counting, arXiv preprint arXiv:2008.03723, pp. 1\u201312"},{"key":"2537_CR9","doi-asserted-by":"crossref","unstructured":"O\u00f1oro-Rubio D, L\u00f3pez-Sastre RJ (2016) Towards perspective-free object counting with deep learning,\u201d European Conference on Computer Vision, pp. 615\u2013629","DOI":"10.1007\/978-3-319-46478-7_38"},{"key":"2537_CR10","unstructured":"Kang D, Chan A (2018) Crowd counting by adaptively fusing predictions from an image pyramid,\u201d arXiv preprint arXiv:1805.06115, pp. 1\u201312"},{"key":"2537_CR11","doi-asserted-by":"crossref","unstructured":"Marsden M, McGuiness K, Little S, O\u2019Connor NE (2017) Fully convolutional crowd counting on highly congested scenes,\u201d 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP), pp. 27\u201333","DOI":"10.5220\/0006097300270033"},{"key":"2537_CR12","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network, IEEE Conference on Computer Vision and Pattern Recognition, pp. 6230\u20136239","DOI":"10.1109\/CVPR.2017.660"},{"issue":"4","key":"2537_CR13","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Machine Intell 40(4):834\u2013848","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"2537_CR14","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions,\u201d arXiv preprint arXiv:1511.07122, pp. 1\u201313"},{"key":"2537_CR15","doi-asserted-by":"crossref","unstructured":"Isola P, Zhu JY, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks, In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134","DOI":"10.1109\/CVPR.2017.632"},{"key":"2537_CR16","doi-asserted-by":"crossref","unstructured":"Shen Z, Xu Y, Ni B, Wang M, Hu J, Yang X (2018) Crowd counting via adversarial cross-scale consistency pursuit, 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5245\u20135254","DOI":"10.1109\/CVPR.2018.00550"},{"key":"2537_CR17","doi-asserted-by":"crossref","unstructured":"Idrees H, Tayyab M, Athrey K, Zhang D, Al-Maddeed S, Rajpoot N, Shah M (2018) Composition loss for counting, density map estimation and localization in dense crowds,\u201d IEEE European Conference on Computer Vision, pp. 544\u2013559","DOI":"10.1007\/978-3-030-01216-8_33"},{"issue":"1","key":"2537_CR18","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/TCI.2016.2644865","volume":"3","author":"H Zhao","year":"2017","unstructured":"Zhao H, Gallo O, Frosio I, Kautz J (2017) Loss functions for image restoration with neural networks. IEEE Trans Computational Imaging 3(1):47\u201357","journal-title":"IEEE Trans Computational Imaging"},{"issue":"4","key":"2537_CR19","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600\u2013612","journal-title":"IEEE Trans Image Process"},{"key":"2537_CR20","doi-asserted-by":"crossref","unstructured":"Loy CC, Chen K, Gong S, Xiang T (2013) Crowd counting and profiling: methodology and evaluation,\u201d Modeling, Simulation and Visual Analysis of Crowds, Springer, pp. 347\u2013382","DOI":"10.1007\/978-1-4614-8483-7_14"},{"issue":"2","key":"2537_CR21","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s11263-005-6644-8","volume":"63","author":"P Viola","year":"2005","unstructured":"Viola P, Jones MJ, Snow D (2005) Detecting pedestrians using patterns of motion and appearance. Int J Comput Vis 63(2):153\u2013161","journal-title":"Int J Comput Vis"},{"key":"2537_CR22","doi-asserted-by":"crossref","unstructured":"Li M, Zhang Z, Huang K Tan T (2008) Estimating the number of people in crowded scenes by mid based foreground segmentation and head-shoulder detection,\u201d 19th International Conference on Pattern Recognition, pp. 1\u20134","DOI":"10.1109\/ICPR.2008.4761705"},{"issue":"6","key":"2537_CR23","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1109\/3468.983420","volume":"31","author":"S Lin","year":"2001","unstructured":"Lin S, Chen J-Y, Chao H-X (2001) Estimation of number of people in crowded scenes using perspective transformation. IEEE Trans Syst Man Cybern Syst Hum 31(6):645\u2013654","journal-title":"IEEE Trans Syst Man Cybern Syst Hum"},{"key":"2537_CR24","doi-asserted-by":"crossref","unstructured":"Chan AB, Liang Z-SJ, Vasconcelos N (2008) Privacy preserving crowd monitoring: Counting people without people models or tracking,\u201d IEEE Conference on Computer Vision and Pattern Recognition, pp. 1\u20137","DOI":"10.1109\/CVPR.2008.4587569"},{"issue":"4","key":"2537_CR25","doi-asserted-by":"publisher","first-page":"2160","DOI":"10.1109\/TIP.2011.2172800","volume":"21","author":"AB Chan","year":"2012","unstructured":"Chan AB, Vasconcelos N (2012) Counting people with low level features and bayesian regression. IEEE Trans Image Process 21(4):2160\u20132177","journal-title":"IEEE Trans Image Process"},{"key":"2537_CR26","doi-asserted-by":"crossref","unstructured":"Ryan D, Denman S, Fookes C, Sridharan S (2009) Crowd counting using multiple local features, Digital Image Computing: Techniques and Applications, pp. 81-88","DOI":"10.1109\/DICTA.2009.22"},{"key":"2537_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2014.07.008","volume":"130","author":"D Ryan","year":"2015","unstructured":"Ryan D, Denman S, Sridharan S, Fookes C (2015) An evaluation of crowd counting methods, features and regression models. Comput Vis Image Underst 130:1\u201317","journal-title":"Comput Vis Image Underst"},{"key":"2537_CR28","doi-asserted-by":"crossref","unstructured":"Pham V-Q, Kozakaya T, Yamaguchi O, Okada R (2015) Count forest: co-voting uncertain number of targets using random forest for crowd density estimation, IEEE International Conference on Computer Vision, pp. 3253\u20133261","DOI":"10.1109\/ICCV.2015.372"},{"key":"2537_CR29","doi-asserted-by":"crossref","unstructured":"Zhang C, Li H, Wang X, Yang X (2015) Cross-scene crowd counting via deep convolutional neural networks. IEEE Confer Comput Vision Pattern Recogn:833\u2013841","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"2537_CR30","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1016\/j.neucom.2018.12.047","volume":"332","author":"L Wang","year":"2019","unstructured":"Wang L, Yin B, Tang X, Li Y (2019) Removing background interference for crowd counting via de-background detail convolutional network. Neurocomputing 332:360\u2013371","journal-title":"Neurocomputing"},{"key":"2537_CR31","unstructured":"Shi M, Yang Z, Xu C, Chen Q (2018) Revisiting perspective information for efficient crowd counting,\u201d arXiv preprint arXiv: 1807.01989, pp. 1\u201310"},{"key":"2537_CR32","doi-asserted-by":"crossref","unstructured":"Cao X, Wang Z, Zhao Y, Su F (2018) Scale aggregation network for accurate and efficient crowd counting, European Conference on Computer Vision, pp. 757\u2013773","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"2537_CR33","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang X, Chen D (2018) CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes, IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp:1091\u20131100","DOI":"10.1109\/CVPR.2018.00120"},{"key":"2537_CR34","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556, pp. 1\u201314"},{"key":"2537_CR35","doi-asserted-by":"crossref","unstructured":"P. Wang, P. Chen, Y. Yuan, D. Liu, Z. Huang, X. Hou, and G. Cottrell (2018) Understanding convolution for semantic segmentation,\u201d IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1451\u20131460","DOI":"10.1109\/WACV.2018.00163"},{"key":"2537_CR36","doi-asserted-by":"crossref","unstructured":"Idrees H, Saleemi I, Seibert C, Shah M (2013) Multi-source multi-scale counting in extremely dense crowd images, IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2547\u20132554","DOI":"10.1109\/CVPR.2013.329"},{"key":"2537_CR37","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet: classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, pp. 1097\u20131105"},{"key":"2537_CR38","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1007\/978-3-642-35289-8_32","volume-title":"A Practical Guide to Training Restricted Boltzmann Machines, Neural Networks: Tricks of the Trade","author":"GE Hinton","year":"2012","unstructured":"Hinton GE (2012) A Practical Guide to Training Restricted Boltzmann Machines, Neural Networks: Tricks of the Trade. Springer, Berlin, pp 599\u2013619"},{"key":"2537_CR39","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/978-3-642-35289-8_26","volume-title":"Practical recommendations for gradient-based training of deep architectures, Neural networks: Tricks of the Trade","author":"Y Bengio","year":"2012","unstructured":"Bengio Y (2012) Practical recommendations for gradient-based training of deep architectures, Neural networks: Tricks of the Trade. Springer, Berlin, pp 437\u2013478"},{"key":"2537_CR40","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks,\u201d Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp. 249\u2013256"},{"issue":"1","key":"2537_CR41","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1109\/TII.2019.2935244","volume":"16","author":"J Li","year":"2020","unstructured":"Li J, Xue Y, Wang W, Ouyang G (2020) Cross-level parallel network for crowd counting. IEEE Trans Indust Informatics 16(1):566\u2013576","journal-title":"IEEE Trans Indust Informatics"},{"key":"2537_CR42","doi-asserted-by":"crossref","unstructured":"Zeng X, Wu Y, Hu S, Wang R, Ye Y (2020) DSPNet: Deep scale purifier network for dense crowd counting, Expert Systems With Applications, pp. 1\u201310","DOI":"10.1016\/j.eswa.2019.112977"},{"key":"2537_CR43","doi-asserted-by":"crossref","unstructured":"Wang Q, Gao J, Lin W, Yuan Y (2020) Pixel-Wise Crowd Understanding via Synthetic Data,\u201d International Journal of Computer Vision, pp. 1\u201321","DOI":"10.1007\/s11263-020-01365-4"},{"key":"2537_CR44","doi-asserted-by":"crossref","unstructured":"Sindagi VA, Patel VM (2017) CNN-based cascaded multi-task learning of high-level prior and density estimation for crowd counting, 14th International Conference on Advanced Video and Signal Based Surveillance, pp. 1\u20136","DOI":"10.1109\/AVSS.2017.8078491"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02537-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-02537-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-02537-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T01:16:48Z","timestamp":1642987008000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-02537-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,29]]},"references-count":44,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["2537"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-02537-6","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,29]]},"assertion":[{"value":"17 May 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}