{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:19:49Z","timestamp":1775067589568,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T00:00:00Z","timestamp":1631059200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T00:00:00Z","timestamp":1631059200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Natural Science Foundation of the Jiangsu Higher Education Institutions of China","award":["19KJA550002"],"award-info":[{"award-number":["19KJA550002"]}]},{"DOI":"10.13039\/501100010014","name":"Six Talent Peaks Project in Jiangsu Province","doi-asserted-by":"publisher","award":["XYDXX-054"],"award-info":[{"award-number":["XYDXX-054"]}],"id":[{"id":"10.13039\/501100010014","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012246","name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012246","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s00521-021-06458-w","type":"journal-article","created":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T18:02:36Z","timestamp":1631124156000},"page":"1407-1422","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Deeper multi-column dilated convolutional network for congested crowd understanding"],"prefix":"10.1007","volume":"34","author":[{"given":"Leilei","family":"Yan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7914-0679","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohan","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanzhang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,8]]},"reference":[{"key":"6458_CR1","doi-asserted-by":"crossref","unstructured":"Babu\u00a0Sam D, Sajjan NN, Venkatesh\u00a0Babu R, Srinivasan M (2018) Divide and grow: Capturing huge diversity in crowd images with incrementally growing cnn. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3618\u20133626","DOI":"10.1109\/CVPR.2018.00381"},{"key":"6458_CR2","doi-asserted-by":"crossref","unstructured":"Boominathan L, Kruthiventi SS, Babu RV (2016) CrowdNet: A deep convolutional network for dense crowd counting. In: Proceedings of the 24th ACM International Conference on Multimedia, pp 640\u2013644","DOI":"10.1145\/2964284.2967300"},{"key":"6458_CR3","doi-asserted-by":"crossref","unstructured":"Cao X, Wang Z, Zhao Y, Su F (2018) Scale aggregation network for accurate and efficient crowd counting. In: Proceedings of the European Conference on Computer Vision, pp 757\u2013773","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"6458_CR4","doi-asserted-by":"crossref","unstructured":"Chan AB, Liang ZSJ, Vasconcelos N (2008) Privacy preserving crowd monitoring: Counting people without people models or tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1\u20137","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"6458_CR5","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1016\/j.neucom.2019.11.064","volume":"382","author":"J Chen","year":"2020","unstructured":"Chen J, Su W, Wang Z (2020) Crowd counting with crowd attention convolutional neural network. Neurocomputing 382:210\u2013220","journal-title":"Neurocomputing"},{"key":"6458_CR6","doi-asserted-by":"crossref","unstructured":"Chen K, Loy CC, Gong S, Xiang T (2012) Feature mining for localised crowd counting. In: Proceedings of the British Machine Vision Conference, vol\u00a01, p\u00a03","DOI":"10.5244\/C.26.21"},{"issue":"4","key":"6458_CR7","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2017) 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":"6458_CR8","unstructured":"Chen, L.C., Papandreou, G., Schroff, F., Adam, H.: Rethinking atrous convolution for semantic image segmentation. In: arXiv preprint arXiv:1706.05587 (2017)"},{"key":"6458_CR9","doi-asserted-by":"crossref","unstructured":"Chu X, Yang W, Ouyang W, Ma C, Yuille AL, Wang X (2017) Multi-context attention for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1831\u20131840","DOI":"10.1109\/CVPR.2017.601"},{"key":"6458_CR10","doi-asserted-by":"crossref","unstructured":"Cire\u015fan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3642\u20133649","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"6458_CR11","doi-asserted-by":"crossref","unstructured":"Cristianini N, Shawe-Taylor J et\u00a0al. (2000) An introduction to support vector machines and other kernel-based learning methods. Cambridge University","DOI":"10.1017\/CBO9780511801389"},{"key":"6458_CR12","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"issue":"4","key":"6458_CR13","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","volume":"34","author":"P Dollar","year":"2011","unstructured":"Dollar P, Wojek C, Schiele B, Perona P (2011) Pedestrian detection: An evaluation of the state of the art. IEEE Trans Pattern Anal Machine Intell 34(4):743\u2013761","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"6458_CR14","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.ins.2020.04.001","volume":"528","author":"L Dong","year":"2020","unstructured":"Dong L, Zhang H, Ji Y, Ding Y (2020) Crowd counting by using multi-level density-based spatial information: A multi-scale cnn framework. Inf Sci 528:79\u201391","journal-title":"Inf Sci"},{"issue":"11","key":"6458_CR15","doi-asserted-by":"publisher","first-page":"2188","DOI":"10.1109\/TPAMI.2011.70","volume":"33","author":"J Gall","year":"2011","unstructured":"Gall J, Yao A, Razavi N, Van Gool L, Lempitsky V (2011) Hough forests for object detection, tracking, and action recognition. IEEE Trans Pattern Anal Machine Intell 33(11):2188\u20132202","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"6458_CR16","doi-asserted-by":"crossref","unstructured":"Idrees H, Saleemi I, Seibert C, Shah M (2013) Multi-source multi-scale counting in extremely dense crowd images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2547\u20132554","DOI":"10.1109\/CVPR.2013.329"},{"key":"6458_CR17","doi-asserted-by":"crossref","unstructured":"Idrees H, Tayyab M, Athrey K, Zhang D, Al-Maadeed S, Rajpoot N, Shah M (2018) Composition loss for counting, density map estimation and localization in dense crowds. In: Proceedings of the European Conference on Computer Vision, pp 532\u2013546","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"6458_CR18","doi-asserted-by":"crossref","unstructured":"Jiang X, Xiao Z, Zhang B, Zhen X, Cao X, Doermann D, Shao L (2019) Crowd counting and density estimation by trellis encoder-decoder networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 6133\u20136142","DOI":"10.1109\/CVPR.2019.00629"},{"issue":"5","key":"6458_CR19","doi-asserted-by":"publisher","first-page":"1408","DOI":"10.1109\/TCSVT.2018.2837153","volume":"29","author":"D Kang","year":"2018","unstructured":"Kang D, Ma Z, Chan AB (2018) Beyond counting: Comparisons of density maps for crowd analysis tasks-counting, detection, and tracking. IEEE Trans Circuits Syst Video Technol 29(5):1408\u20131422","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"6458_CR20","unstructured":"Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In: International Conference on Learning Representations"},{"key":"6458_CR21","first-page":"878","volume":"1","author":"B Leibe","year":"2005","unstructured":"Leibe B, Seemann E, Schiele B (2005) Pedestrian detection in crowded scenes. Proceed IEEE Conf Comput Vision Pattern Recogn 1:878\u2013885","journal-title":"Proceed IEEE Conf Comput Vision Pattern Recogn"},{"key":"6458_CR22","unstructured":"Lempitsky V, Zisserman A (2010) Learning to count objects in images. In: Advances in Neural Information Processing Systems, pp 1324\u20131332"},{"key":"6458_CR23","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang X, Chen D (2018) CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1091\u20131100","DOI":"10.1109\/CVPR.2018.00120"},{"key":"6458_CR24","doi-asserted-by":"crossref","unstructured":"Liu N, Long Y, Zou C, Niu Q, Pan L, Wu H (2019) ADCrowdnet: An attention-injective deformable convolutional network for crowd understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3225\u20133234","DOI":"10.1109\/CVPR.2019.00334"},{"key":"6458_CR25","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/j.neucom.2019.03.065","volume":"350","author":"J Ma","year":"2019","unstructured":"Ma J, Dai Y, Tan YP (2019) Atrous convolutions spatial pyramid network for crowd counting and density estimation. Neurocomputing 350:91\u2013101","journal-title":"Neurocomputing"},{"key":"6458_CR26","doi-asserted-by":"crossref","unstructured":"Marsden M, McGuinness K, Little S, O\u2019Connor NE (2016) Fully convolutional crowd counting on highly congested scenes. In: arXiv preprint arXiv:1612.00220","DOI":"10.5220\/0006097300270033"},{"key":"6458_CR27","doi-asserted-by":"crossref","unstructured":"Onoro-Rubio D, L\u00f3pez-Sastre RJ (2016) Towards perspective-free object counting with deep learning. In: Proceedings of the European Conference on Computer Vision, pp 615\u2013629","DOI":"10.1007\/978-3-319-46478-7_38"},{"key":"6458_CR28","doi-asserted-by":"crossref","unstructured":"Paragios N, Ramesh V (2001) A MRF-based approach for real-time subway monitoring. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol\u00a01, pp I\u20131034","DOI":"10.1109\/CVPR.2001.990644"},{"key":"6458_CR29","doi-asserted-by":"crossref","unstructured":"Pham VQ, Kozakaya T, Yamaguchi O, Okada R (2015) Count forest: Co-voting uncertain number of targets using random forest for crowd density estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp 3253\u20133261","DOI":"10.1109\/ICCV.2015.372"},{"key":"6458_CR30","first-page":"4031","volume":"1","author":"DB Sam","year":"2017","unstructured":"Sam DB, Surya S, Babu RV (2017) Switching convolutional neural network for crowd counting. Proceed IEEE Conf Comput Vision Pattern Recogn 1:4031\u20134039","journal-title":"Proceed IEEE Conf Comput Vision Pattern Recogn"},{"key":"6458_CR31","doi-asserted-by":"crossref","unstructured":"Shang C, Ai H, Bai B (2016) End-to-end crowd counting via joint learning local and global count. In: Proceedings of the IEEE International Conference on Image Processing, pp 1215\u20131219","DOI":"10.1109\/ICIP.2016.7532551"},{"key":"6458_CR32","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations"},{"key":"6458_CR33","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. In: Proceedings of the IEEE International Conference on Advanced Video and Signal Based Surveillance, pp 1\u20136","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"6458_CR34","doi-asserted-by":"crossref","unstructured":"Sindagi VA, Patel VM (2017) Generating high-quality crowd density maps using contextual pyramid cnns. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1861\u20131870","DOI":"10.1109\/ICCV.2017.206"},{"issue":"2","key":"6458_CR35","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1023\/B:VISI.0000013087.49260.fb","volume":"57","author":"P Viola","year":"2004","unstructured":"Viola P, Jones MJ (2004) Robust real-time face detection. Int J Comput Vision 57(2):137\u2013154","journal-title":"Int J Comput Vision"},{"issue":"2","key":"6458_CR36","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 Vision 63(2):153\u2013161","journal-title":"Int J Comput Vision"},{"key":"6458_CR37","doi-asserted-by":"crossref","unstructured":"Walach, E., Wolf, L.: Learning to count with cnn boosting. In: Proceedings of the European Conference on Computer Vision, pp. 660\u2013676 (2016)","DOI":"10.1007\/978-3-319-46475-6_41"},{"key":"6458_CR38","doi-asserted-by":"crossref","unstructured":"Wang P, Chen P, Yuan Y, Liu D, Huang Z, Hou X, Cottrell G (2018) Understanding convolution for semantic segmentation. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp 1451\u20131460","DOI":"10.1109\/WACV.2018.00163"},{"issue":"1","key":"6458_CR39","doi-asserted-by":"publisher","first-page":"1057","DOI":"10.1007\/s11042-019-08208-6","volume":"79","author":"Y Wang","year":"2020","unstructured":"Wang Y, Hu S, Wang G, Chen C, Pan Z (2020) Multi-scale dilated convolution of convolutional neural network for crowd counting. Multimedia Tools Appl 79(1):1057\u20131073","journal-title":"Multimedia Tools Appl"},{"key":"6458_CR40","doi-asserted-by":"crossref","unstructured":"Wang Y, Zou Y (2016) Fast visual object counting via example-based density estimation. In: Proceedings of the IEEE International Conference on Image Processing, pp 3653\u20133657","DOI":"10.1109\/ICIP.2016.7533041"},{"key":"6458_CR41","doi-asserted-by":"crossref","unstructured":"Wei Y, Feng J, Liang X, Cheng MM, Zhao Y, Yan S (2017) Object region mining with adversarial erasing: A simple classification to semantic segmentation approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1568\u20131576","DOI":"10.1109\/CVPR.2017.687"},{"key":"6458_CR42","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/ICCV.2005.74","volume":"1","author":"B Wu","year":"2005","unstructured":"Wu B, Nevatia R (2005) Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. Proceed IEEE Int Conf Comput Vision 1:90\u201397","journal-title":"Proceed IEEE Int Conf Comput Vision"},{"key":"6458_CR43","unstructured":"Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. In: International Conference on Learning Representations"},{"key":"6458_CR44","doi-asserted-by":"publisher","first-page":"112977","DOI":"10.1016\/j.eswa.2019.112977","volume":"141","author":"X Zeng","year":"2020","unstructured":"Zeng X, Wu Y, Hu S, Wang R, Ye Y (2020) Dspnet: deep scale purifier network for dense crowd counting. Expert Syst Appl 141:112977","journal-title":"Expert Syst Appl"},{"issue":"6","key":"6458_CR45","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.1109\/TMM.2016.2542585","volume":"18","author":"C Zhang","year":"2016","unstructured":"Zhang C, Kang K, Li H, Wang X, Xie R, Yang X (2016) Data-driven crowd understanding: A baseline for a large-scale crowd dataset. IEEE Trans Multimedia 18(6):1048\u20131061","journal-title":"IEEE Trans Multimedia"},{"key":"6458_CR46","doi-asserted-by":"crossref","unstructured":"Zhang C, Li H, Wang X, Yang X (2015) Cross-scene crowd counting via deep convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 833\u2013841","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"6458_CR47","doi-asserted-by":"crossref","unstructured":"Zhang S, Wu G, Costeira JP, Moura JM (2017) FCN-rLSTM: Deep spatio-temporal neural networks for vehicle counting in city cameras. In: Proceedings of the IEEE International Conference on Computer Vision, pp 3667\u20133676","DOI":"10.1109\/ICCV.2017.396"},{"key":"6458_CR48","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. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 589\u2013597","DOI":"10.1109\/CVPR.2016.70"},{"issue":"10","key":"6458_CR49","doi-asserted-by":"publisher","first-page":"3651","DOI":"10.1109\/TCSVT.2019.2943010","volume":"30","author":"M Zhao","year":"2020","unstructured":"Zhao M, Zhang C, Zhang J, Porikli F, Ni B, Zhang W (2020) Scale-aware crowd counting via depth-embedded convolutional neural networks. IEEE Trans Circuits Syst Video Technol 30(10):3651\u20133662","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"6458_CR50","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.patrec.2020.05.009","volume":"135","author":"M Zhu","year":"2020","unstructured":"Zhu M, Wang X, Tang J, Wang N, Qu L (2020) Attentive multi-stage convolutional neural network for crowd counting. Pattern Recogn Lett 135:279\u2013285","journal-title":"Pattern Recogn Lett"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06458-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-021-06458-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-021-06458-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,21]],"date-time":"2022-01-21T15:33:19Z","timestamp":1642779199000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-021-06458-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,8]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["6458"],"URL":"https:\/\/doi.org\/10.1007\/s00521-021-06458-w","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,8]]},"assertion":[{"value":"12 October 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and animal rights statement"}}]}}