{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:03:28Z","timestamp":1775912608819,"version":"3.50.1"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T00:00:00Z","timestamp":1641945600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T00:00:00Z","timestamp":1641945600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Public Security Subject Basic Theory Research Project","award":["2021XKZX08"],"award-info":[{"award-number":["2021XKZX08"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2021JKF102"],"award-info":[{"award-number":["2021JKF102"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Fund of the Public Security Behavioral Science Laboratory","award":["2020SYS16"],"award-info":[{"award-number":["2020SYS16"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s00371-021-02383-0","type":"journal-article","created":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T10:02:51Z","timestamp":1641981771000},"page":"1045-1056","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["MSFFA: a multi-scale feature fusion and attention mechanism network for crowd counting"],"prefix":"10.1007","volume":"39","author":[{"given":"Zhaoxin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuhua","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yishan","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingyuan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,12]]},"reference":[{"key":"2383_CR1","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-image crowd counting via multi-column convolutional neural network. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 589\u2013597 (2016)","DOI":"10.1109\/CVPR.2016.70"},{"key":"2383_CR2","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, X., Chen, D.: CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1091\u20131100 (2018)","DOI":"10.1109\/CVPR.2018.00120"},{"key":"2383_CR3","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.: Attentive multi-stage convolutional neural network for crowd counting. Pat. Recognit. Lett. 135, 279\u2013285 (2020)","journal-title":"Pat. Recognit. Lett."},{"key":"2383_CR4","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.patrec.2019.04.012","volume":"125","author":"Y Miao","year":"2019","unstructured":"Miao, Y., Han, J., Gao, Y., Zhang, B.: ST-CNN: Spatial-Temporal convolutional neural network for crowd counting in videos. Pat. Recognit. Lett. 125, 113\u2013118 (2019)","journal-title":"Pat. Recognit. Lett."},{"key":"2383_CR5","doi-asserted-by":"publisher","first-page":"2127","DOI":"10.1007\/s00371-020-01974-7","volume":"37","author":"SD Khan","year":"2021","unstructured":"Khan, S.D., Basalamah, S.: Scale and density invariant head detection deep model for crowd counting in pedestrian crowds. Vis. Comput. 37, 2127\u20132137 (2021)","journal-title":"Vis. Comput."},{"key":"2383_CR6","doi-asserted-by":"crossref","unstructured":"Guo, D., Li, K., Zha, Z. J., Wang, M.: DADNet: Dilated-attention-deformable convnet for crowd counting. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 1823\u20131832 (2019)","DOI":"10.1145\/3343031.3350881"},{"key":"2383_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2019.08.018","volume":"363","author":"J Gao","year":"2019","unstructured":"Gao, J., Wang, Q., Yuan, Y.: SCAR: Spatial-\/channel-wise attention regression networks for crowd counting. Neurocomputing 363, 1\u20138 (2019)","journal-title":"Neurocomputing"},{"issue":"4","key":"2383_CR8","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.: Pedestrian detection: An evaluation of the state of the art Mach. IEEE Trans. Pat. Anal. Mach. Intell. 34(4), 743\u2013761 (2011)","journal-title":"IEEE Trans. Pat. Anal. Mach. Intell."},{"key":"2383_CR9","doi-asserted-by":"crossref","unstructured":"Topkaya, I. S., Erdogan, H., Porikli, F.: Counting people by clustering person detector outputs. In: 2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 313\u2013 318 (2014)","DOI":"10.1109\/AVSS.2014.6918687"},{"key":"2383_CR10","doi-asserted-by":"crossref","unstructured":"Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 878\u2013885 (2005)","DOI":"10.1109\/CVPR.2005.272"},{"issue":"2","key":"2383_CR11","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s11263-006-0027-7","volume":"75","author":"B Wu","year":"2007","unstructured":"Wu, B., Nevatia, R.: Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors. Int. J. Comput. Vision 75(2), 247\u2013266 (2007)","journal-title":"Int. J. Comput. Vision"},{"key":"2383_CR12","doi-asserted-by":"crossref","unstructured":"Idrees, H., Saleemi, I., Seibert, C., Shah, M.: Multi-source multi-scale counting in extremely dense crowd images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2547\u20132554 (2013)","DOI":"10.1109\/CVPR.2013.329"},{"key":"2383_CR13","doi-asserted-by":"crossref","unstructured":"Chan, A. B., Vasconcelos, N.: Bayesian poisson regression for crowd counting. In: IEEE International Conference on Computer Vision (2009)","DOI":"10.1109\/ICCV.2009.5459191"},{"key":"2383_CR14","doi-asserted-by":"crossref","unstructured":"Cao, X., Wang, Z., Zhao, Y., Su, F.: Scale aggregation network for accurate and efficient crowd counting. In: European Conference on Computer Vision (ECCV), pp. 734\u2013750 (2018)","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"2383_CR15","doi-asserted-by":"crossref","unstructured":"Babu Sam, D., Surya, S., Venkatesh Babu, R.: Switching convolutional neural network for crowd counting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4031\u20134039 (2017)","DOI":"10.1109\/CVPR.2017.429"},{"key":"2383_CR16","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.: A multi-scale and multi-level feature aggregation network for crowd counting. Neurocomputing 423, 46\u201356 (2021)","journal-title":"Neurocomputing"},{"key":"2383_CR17","unstructured":"Dai, F., Liu, H., Ma, Y., Cao, J., Zhao, Q., Zhang, Y.: Dense scale network for crowd counting (2019). arXiv preprint https:\/\/arxiv.org\/abs\/1906.09707."},{"key":"2383_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, X., Xiao, Z., Zhang, B., Zhen, X., Cao, X., Doermann, D., Shao, L.: Crowd counting and density estimation by trellis encoder-decoder networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6133\u20136142 (2019)","DOI":"10.1109\/CVPR.2019.00629"},{"key":"2383_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, L., Shi, M., Chen, Q.: Crowd counting via scale adaptive convolutional neural network. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 1113\u20131121 (2018)","DOI":"10.1109\/WACV.2018.00127"},{"issue":"10","key":"2383_CR20","doi-asserted-by":"publisher","first-page":"3486","DOI":"10.1109\/TCSVT.2019.2919139","volume":"30","author":"J Gao","year":"2019","unstructured":"Gao, J., Wang, Q., Li, X.: PCC-net: Perspective crowd counting via spatial convolutional network. IEEE T. Circ. Syst Vid. 30(10), 3486\u20133498 (2019)","journal-title":"IEEE T. Circ. Syst Vid."},{"key":"2383_CR21","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.neucom.2018.10.058","volume":"329","author":"Y Zhang","year":"2019","unstructured":"Zhang, Y., Zhou, C., Chang, F., Kot, A.C.: Multi-resolution attention convolutional neural network for crowd counting. Neurocomputing 329, 144\u2013152 (2019)","journal-title":"Neurocomputing"},{"key":"2383_CR22","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1016\/j.neucom.2020.04.139","volume":"404","author":"S Wang","year":"2020","unstructured":"Wang, S., Lu, Y., Zhou, T., Di, H., Lu, L., Zhang, L.: SCLNet: Spatial context learning network for congested crowd counting. Neurocomputing 404, 227\u2013239 (2020)","journal-title":"Neurocomputing"},{"key":"2383_CR23","unstructured":"Cheng, J., Chen, Z., Zhang, X., Li, Y., Jing, X.: Exploit the potential of multi-column architecture for crowd counting (2020). arXiv preprint arXiv: 2007.05779"},{"key":"2383_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-020-2969-8","volume":"64","author":"J Xie","year":"2021","unstructured":"Xie, J., Pang, Y., Cholakkal, H., Anwer, R., Khan, F., Shao, L.: PSC-Net: Learning part spatial co-occurrence for occluded pedestrian detection. Sci. China Inf. Sci. 64, 1\u201313 (2021)","journal-title":"Sci. China Inf. Sci."},{"key":"2383_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2020.06.034","volume":"411","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Zhang, W., Liu, Y., Zhu, J.: Two-branch fusion network with attention map for crowd counting. Neurocomputing 411, 1\u20138 (2020)","journal-title":"Neurocomputing"},{"key":"2383_CR26","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.: Crowd counting by using multi-level density-based spatial information: A Multi-scale CNN framework. Inf. Sci. 528, 79\u201391 (2020)","journal-title":"Inf. Sci."},{"issue":"1","key":"2383_CR27","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1007\/s10489-020-01842-w","volume":"51","author":"YB Liu","year":"2021","unstructured":"Liu, Y.B., Jia, R.S., Liu, Q.M., Zhang, X.L., Sun, H.M.: Crowd counting method based on the self-attention residual network. Appl. Intell. 51(1), 427\u2013440 (2021)","journal-title":"Appl. Intell."},{"key":"2383_CR28","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv preprint https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"2383_CR29","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J. Y., & Kweon, I. S. Cbam: Convolutional block attention module. In Proceedings of the European conference on computer vision (ECCV), pp.3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"2383_CR30","doi-asserted-by":"crossref","unstructured":"Idrees, H., Tayyab, M., Athrey, K., Zhang, D., Al-Maadeed, S., Rajpoot, N., Shah, M.: Composition loss for counting, density map estimation and localization in dense crowds. In: European Conference on Computer Vision (ECCV), pp. 532\u2013546 (2018)","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"2383_CR31","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.: DSPNet: Deep scale purifier network for dense crowd counting. Expert Syst. Appl. 141, 112977 (2020)","journal-title":"Expert Syst. Appl."},{"key":"2383_CR32","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, Y.P.: Atrous convolutions spatial pyramid network for crowd counting and density estimation. Neurocomputing 350, 91\u2013101 (2019)","journal-title":"Neurocomputing"},{"key":"2383_CR33","doi-asserted-by":"crossref","unstructured":"Luo, A., Yang, F., Li, X., Nie, D., Jiao, Z., Zhou, S., Cheng, H.: Hybrid graph neural networks for crowd counting. In: AAAI Conference on Artificial Intelligence (AAAI), pp 11693\u201311700 (2020)","DOI":"10.1609\/aaai.v34i07.6839"},{"key":"2383_CR34","doi-asserted-by":"crossref","unstructured":"Zeng, L., Xu, X., Cai, B., Qiu, S., & Zhang, T.: Multi-scale convolutional neural networks for crowd counting. In: Proceedings of the IEEE International Conference on Image Processing, pp. 465\u2013469 (2017)","DOI":"10.1109\/ICIP.2017.8296324"},{"key":"2383_CR35","doi-asserted-by":"crossref","unstructured":"Oh, M. H., Olsen, P., Ramamurthy, K. N.: Crowd counting with decomposed uncertainty. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 11799\u201311806 (2020)","DOI":"10.1609\/aaai.v34i07.6852"},{"key":"2383_CR36","doi-asserted-by":"crossref","unstructured":"Sindagi, V. A., Patel, V. M.: 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 (2017)","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"2383_CR37","unstructured":"Sam, D. B., Peri, S. V., Sundararaman, M. N., Kamath, A., Radhakrishnan, V. B.: Locate, size and count: accurately resolving people in dense crowds via detection. IEEE Trans. Pattern Anal. Mach. Intell., (2020)"},{"key":"2383_CR38","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.neucom.2021.04.045","volume":"451","author":"B Zhang","year":"2021","unstructured":"Zhang, B., Wang, N., Zhao, Z., Abraham, A., Liu, H.: Crowd counting based on attention-guided multi-scale fusion networks. Neurocomputing 451, 12\u201324 (2021)","journal-title":"Neurocomputing"},{"key":"2383_CR39","doi-asserted-by":"crossref","unstructured":"Liu, L., Qiu, Z., Li, G., Liu, S., Ouyang, W., & Lin, L: Crowd counting with deep structured scale integration network. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 1774\u20131783 (2019)","DOI":"10.1109\/ICCV.2019.00186"},{"key":"2383_CR40","doi-asserted-by":"crossref","unstructured":"Ma, Z., Wei, X., Hong, X., & Gong, Y. Bayesian loss for crowd count estimation with point supervision. In Proceedings of the IEEE International Conference on Computer Vision. pp. 6142\u20136151 (2019)","DOI":"10.1109\/ICCV.2019.00624"},{"key":"2383_CR41","doi-asserted-by":"crossref","unstructured":"Jiang, X., Zhang, L., Xu, M., Zhang, T., Lv, P., Zhou, B., & Pang, Y. Attention scaling for crowd counting. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.4706\u20134715 (2020)","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"2383_CR42","doi-asserted-by":"crossref","unstructured":"Zhou, J. T., Zhang, L., Du, J., Peng, X., Fang, Z., Xiao, Z., Zhu, H.: Locality-Aware Crowd Counting, IEEE Trans. Pattern Anal. Mach. Intell., (2021)","DOI":"10.1109\/TPAMI.2021.3056518"},{"key":"2383_CR43","doi-asserted-by":"crossref","unstructured":"Wan, J., Liu, Z., Chant, A. B.: A Generalized Loss Function for Crowd Counting and Localization, In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp.1974\u20131983 (2021)","DOI":"10.1109\/CVPR46437.2021.00201"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02383-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-021-02383-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-021-02383-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T03:57:56Z","timestamp":1726459076000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-021-02383-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,12]]},"references-count":43,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["2383"],"URL":"https:\/\/doi.org\/10.1007\/s00371-021-02383-0","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,12]]},"assertion":[{"value":"14 December 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflicts of interest to declare relevant to the contents of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}