{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:06:58Z","timestamp":1774872418808,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T00:00:00Z","timestamp":1645488000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Humanity and Social Science Foundation of Ministry of Education, China","award":["21YJAZH077"],"award-info":[{"award-number":["21YJAZH077"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s10489-022-03187-y","type":"journal-article","created":{"date-parts":[[2022,2,22]],"date-time":"2022-02-22T10:02:59Z","timestamp":1645524179000},"page":"13097-13113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Crowd density estimation based on multi scale features fusion network with reverse attention mechanism"],"prefix":"10.1007","volume":"52","author":[{"given":"Yong-Chao","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1612-4764","authenticated-orcid":false,"given":"Rui-Sheng","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Ying-Xiang","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Dong-Nuo","family":"Han","sequence":"additional","affiliation":[]},{"given":"Hong-Mei","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,22]]},"reference":[{"issue":"10","key":"3187_CR1","doi-asserted-by":"publisher","first-page":"2814","DOI":"10.1109\/TCSVT.2017.2731866","volume":"28","author":"M Xu","year":"2017","unstructured":"Xu M, Li C, Lv P, Lin N, Hou R, Zhou B (2017) An efficient method of crowd aggregation computation in public areas. IEEE Trans Circuits Syst Video Technol 28(10):2814\u20132825","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"10","key":"3187_CR2","doi-asserted-by":"publisher","first-page":"1986","DOI":"10.1109\/TPAMI.2015.2396051","volume":"37","author":"H Idrees","year":"2015","unstructured":"Idrees H, Soomro K, Shah M (2015) Detecting humans in dense crowds using locally-consistent scale prior and global occlusion reasoning. IEEE Trans Pattern Anal Mach Intell 37(10):1986\u20131998","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3187_CR3","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\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) 2547\u20132554","DOI":"10.1109\/CVPR.2013.329"},{"key":"3187_CR4","doi-asserted-by":"publisher","first-page":"106214","DOI":"10.1016\/j.knosys.2020.106214","volume":"209","author":"C Hu","year":"2020","unstructured":"Hu C, Wang Y, Gu J (2020) Cross-domain intelligent fault classification of bearings based on tensor-aligned invariant subspace learning and two-dimensional convolutional neural networks. Knowledge-Based Systems 209:106214","journal-title":"Knowledge-Based Systems"},{"issue":"4","key":"3187_CR5","doi-asserted-by":"publisher","first-page":"2609","DOI":"10.1007\/s10489-020-02011-9","volume":"51","author":"C Hu","year":"2021","unstructured":"Hu C, He S, Wang Y (2021) A classification method to detect faults in a rotating machinery based on kernelled support tensor machine and multilinear principal component analysis. Appl Intell 51(4):2609\u20132621","journal-title":"Appl Intell"},{"key":"3187_CR6","doi-asserted-by":"crossref","unstructured":"Babu Sam D, Surya S, Venkatesh Babu R (2017). Switching convolutional neural network for crowd density estimation. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(CVPR) 5744\u20135752","DOI":"10.1109\/CVPR.2017.429"},{"key":"3187_CR7","doi-asserted-by":"crossref","unstructured":"Onoro-Rubio D, L\u00f3pez-Sastre RJ (2016). Towards perspective-free object counting with deep learning. In\u00a0European conference on computer vision. Springer, Cham, 615\u2013629","DOI":"10.1007\/978-3-319-46478-7_38"},{"issue":"10","key":"3187_CR8","doi-asserted-by":"publisher","first-page":"3360","DOI":"10.1007\/s10489-018-1150-1","volume":"48","author":"L Wang","year":"2018","unstructured":"Wang L, Yin B, Guo A, Ma H, Cao J (2018) Skip-connection convolutional neural network for still image crowd density estimation. Appl Intell 48(10):3360\u20133371","journal-title":"Appl Intell"},{"key":"3187_CR9","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.neucom.2021.06.055","volume":"459","author":"M Jiang","year":"2021","unstructured":"Jiang M, Lin J, Wang ZJ (2021) A smartly simple way for joint crowd counting and localization. Neurocomputing 459:35\u201343","journal-title":"Neurocomputing"},{"key":"3187_CR10","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.neucom.2021.06.086","volume":"459","author":"Y Xia","year":"2021","unstructured":"Xia Y, He Y, Peng S, Hao X, Yang Q, Yin B (2021) EDENet: Elaborate density estimation network for crowd counting. Neurocomputing 459:108\u2013121","journal-title":"Neurocomputing"},{"key":"3187_CR11","doi-asserted-by":"crossref","unstructured":"Wang W, Liu Q, Wang W (2021). Pyramid-dilated deep convolutional neural network for crowd counting.\u00a0Appl Intell 1\u201313","DOI":"10.3390\/sym13040703"},{"key":"3187_CR12","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/j.neucom.2021.04.037","volume":"451","author":"S Amirgholipour","year":"2021","unstructured":"Amirgholipour S, Jia W, Liu L, Fan X, Wang D, He X (2021) PDANet: Pyramid density-aware attention based network for accurate crowd counting. Neurocomputing 451:215\u2013230","journal-title":"Neurocomputing"},{"key":"3187_CR13","doi-asserted-by":"crossref","unstructured":"Zhang Y, Zhou D, Chen S, Gao S, Ma Y (2016). Single-image crowd density estimation via multi-column convolutional neural network. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(CVPR) 589\u2013597","DOI":"10.1109\/CVPR.2016.70"},{"key":"3187_CR14","doi-asserted-by":"crossref","unstructured":"Li Y, Zhang X, Chen D (2018). Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(CVPR) 1091\u20131100","DOI":"10.1109\/CVPR.2018.00120"},{"issue":"12","key":"3187_CR15","doi-asserted-by":"publisher","first-page":"567","DOI":"10.3390\/info11120567","volume":"11","author":"P Nie","year":"2020","unstructured":"Nie P, Fan C, Zou L, Chen L, Li X (2020) crowd density estimation Guided by Attention Network. Information 11(12):567","journal-title":"Information"},{"issue":"17","key":"3187_CR16","doi-asserted-by":"publisher","first-page":"3466","DOI":"10.3390\/app9173466","volume":"9","author":"Y Zhang","year":"2019","unstructured":"Zhang Y, Li G, Lei J, He J (2019) FDCNet: Frontend-backend fusion dilated network through channel-attention mechanism. Appl Sci 9(17):3466","journal-title":"Appl Sci"},{"issue":"3","key":"3187_CR17","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1109\/TCSVT.2014.2358029","volume":"25","author":"T Li","year":"2014","unstructured":"Li T, Chang H, Wang M, Ni B, Hong R, Yan S (2014) Crowded scene analysis: A survey. IEEE Trans Circuits Syst Video Technol 25(3):367\u2013386","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"3187_CR18","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 density estimation via de-background detail convolutional network. Neurocomputing 332:360\u2013371","journal-title":"Neurocomputing"},{"issue":"6","key":"3187_CR19","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1109\/3468.983420","volume":"31","author":"SF Lin","year":"2001","unstructured":"Lin SF, Chen JY, Chao HX (2001) Estimation of number of people in crowded scenes using perspective transformation. IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans 31(6):645\u2013654","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans"},{"key":"3187_CR20","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005). Histograms of oriented gradients for human detection. In\u00a02005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), Vol. 1, pp. 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"3187_CR21","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. In\u00a02008 19th international conference on pattern recognition\u00a0(ICPR), 1\u20134. IEEE","DOI":"10.1109\/ICPR.2008.4761705"},{"issue":"9","key":"3187_CR22","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2009","unstructured":"Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D (2009) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627\u20131645","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"4","key":"3187_CR23","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 Mach Intell 34(4):743\u2013761","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3187_CR24","doi-asserted-by":"crossref","unstructured":"An S, Liu W, Venkatesh S (2007). Face recognition using kernel ridge regression. In\u00a02007 IEEE Conference on Computer Vision and Pattern Recognition\u00a0(CVPR), 1\u20137","DOI":"10.1109\/CVPR.2007.383105"},{"key":"3187_CR25","doi-asserted-by":"crossref","unstructured":"Chan AB, Vasconcelos N (2009). Bayesian poisson regression for crowd density estimation. In\u00a02009 IEEE 12th international conference on computer vision\u00a0(ICCV) 545\u2013551","DOI":"10.1109\/ICCV.2009.5459191"},{"key":"3187_CR26","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\u00a0Proceedings of the IEEE International Conference on Computer Vision\u00a0(ICCV), 3253\u20133261","DOI":"10.1109\/ICCV.2015.372"},{"key":"3187_CR27","first-page":"1324","volume":"23","author":"V Lempitsky","year":"2010","unstructured":"Lempitsky V, Zisserman A (2010) Learning to count objects in images. Adv Neural Inf Process Syst 23:1324\u20131332","journal-title":"Adv Neural Inf Process Syst"},{"issue":"4","key":"3187_CR28","doi-asserted-by":"publisher","first-page":"2160","DOI":"10.1109\/TIP.2011.2172800","volume":"21","author":"AB Chan","year":"2011","unstructured":"Chan AB, Vasconcelos N (2011) Counting people with low-level features and Bayesian regression. IEEE Trans Image Process 21(4):2160\u20132177","journal-title":"IEEE Trans Image Process"},{"key":"3187_CR29","unstructured":"Zhang C, Li H, Wang X, Yang X (2015). Cross-scene crowd density estimation via deep convolutional neural networks. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(CVPR), 833\u2013841"},{"key":"3187_CR30","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 density estimation. In\u00a02017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) 1\u20136. IEEE","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"3187_CR31","doi-asserted-by":"crossref","unstructured":"Liu W, Salzmann M, Fua P (2019) Context-aware crowd density estimation. In\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0(CVPR) 5099\u20135108","DOI":"10.1109\/CVPR.2019.00524"},{"key":"3187_CR32","doi-asserted-by":"crossref","unstructured":"Wang Q, Gao J, Lin W, Yuan Y (2019) Learning from synthetic data for crowd density estimation in the wild. In\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0(CVPR) 8198\u20138207","DOI":"10.1109\/CVPR.2019.00839"},{"key":"3187_CR33","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.neucom.2020.09.059","volume":"423","author":"F Zhu","year":"2021","unstructured":"Zhu F, Yan H, Chen X, Li T, Zhang Z (2021) A multi-scale and multi-level feature aggregation network for crowd counting. Neurocomputing 423:46\u201356","journal-title":"Neurocomputing"},{"issue":"1","key":"3187_CR34","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/s10489-020-01842-w","volume":"51","author":"YB Liu","year":"2021","unstructured":"Liu YB, Jia RS, Liu QM, Zhang XL, Sun HM (2021) Crowd counting method based on the self-attention residual network. Appl Intell 51(1):427\u2013440","journal-title":"Appl Intell"},{"key":"3187_CR35","doi-asserted-by":"crossref","unstructured":"Gu L, Pang C, Zheng Y, Lyu C, Lyu L (2021) Context-aware pyramid attention network for crowd counting.\u00a0Appl Intell.1\u201317","DOI":"10.1007\/s10489-021-02639-1"},{"key":"3187_CR36","unstructured":"Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhudinov R, ..., Bengio Y (2015) Show, attend and tell: Neural image caption generation with visual attention. In\u00a0International conference on machine learning\u00a0(2048\u20132057). PMLR"},{"key":"3187_CR37","doi-asserted-by":"crossref","unstructured":"Sindagi VA, Patel VM (2019). Inverse attention guided deep crowd density estimation network. In\u00a02019 16th IEEE international conference on advanced video and signal based surveillance (AVSS) 1\u20138. IEEE","DOI":"10.1109\/AVSS.2019.8909889"},{"issue":"11","key":"3187_CR38","doi-asserted-by":"publisher","first-page":"3777","DOI":"10.3390\/s21113777","volume":"21","author":"Y Zhang","year":"2021","unstructured":"Zhang Y, Zhao H, Duan Z, Huang L, Deng J, Zhang Q (2021) Congested crowd density estimation via Adaptive Multi-Scale Context Learning. Sensors 21(11):3777","journal-title":"Sensors"},{"key":"3187_CR39","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1109\/TMM.2020.2992979","volume":"23","author":"L Liu","year":"2020","unstructured":"Liu L, Jiang J, Jia W, Amirgholipour S, Wang Y, Zeibots M, He X (2020) Denet: A universal network for counting crowd with varying densities and scales. IEEE Trans Multimedia 23:1060\u20131068","journal-title":"IEEE Trans Multimedia"},{"key":"3187_CR40","doi-asserted-by":"crossref","unstructured":"Shen Z, Xu Y, Ni B, Wang M, Hu J, Yang X (2018) crowd density estimation via adversarial cross-scale consistency pursuit. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(CVPR), 5245\u20135254","DOI":"10.1109\/CVPR.2018.00550"},{"key":"3187_CR41","doi-asserted-by":"crossref","unstructured":"Sindagi VA, Patel VM (2017) Generating high-quality crowd density maps using contextual pyramid cnns. In\u00a0Proceedings of the IEEE international conference on computer vision\u00a0(ICCV) 1861\u20131870","DOI":"10.1109\/ICCV.2017.206"},{"key":"3187_CR42","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 density estimation. In\u00a02017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) 1\u20136","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"3187_CR43","doi-asserted-by":"crossref","unstructured":"Sam DB, Sajjan NN, Babu RV, Srinivasan M (2018) Divide and grow: Capturing huge diversity in crowd images with incrementally growing cnn. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(CVPR) 3618\u20133626","DOI":"10.1109\/CVPR.2018.00381"},{"key":"3187_CR44","doi-asserted-by":"crossref","unstructured":"Cao X, Wang Z, Zhao Y, Su F (2018). Scale aggregation network for accurate and efficient crowd density estimation. In\u00a0Proceedings of the European Conference on Computer Vision (ECCV) 734\u2013750","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"3187_CR45","doi-asserted-by":"crossref","unstructured":"Shi Z, Zhang L, Liu Y, Cao X, Ye Y, Cheng MM, Zheng G (2018) crowd density estimation with deep negative correlation learning. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition\u00a0(CVPR) 5382\u20135390","DOI":"10.1109\/CVPR.2018.00564"},{"issue":"6","key":"3187_CR46","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1049\/ipr2.12099","volume":"15","author":"J Chen","year":"2021","unstructured":"Chen J, Wang Z (2021) Crowd counting with segmentation attention convolutional neural network. IET Image Proc 15(6):1221\u20131231","journal-title":"IET Image Proc"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03187-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-03187-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-03187-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T12:43:09Z","timestamp":1663332189000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-03187-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,22]]},"references-count":46,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["3187"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-03187-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,22]]},"assertion":[{"value":"4 January 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 February 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}