{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T04:08:29Z","timestamp":1744862909415,"version":"3.40.4"},"reference-count":77,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T00:00:00Z","timestamp":1727913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61675161"],"award-info":[{"award-number":["61675161"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shaanxi Provincial Key Research and Development Program Key Industrial Innovation Chain (Cluster)- Industrial Field Project","award":["2023-ZDLGY-22"],"award-info":[{"award-number":["2023-ZDLGY-22"]}]},{"name":"the Innovation Capability Support Program of Shaanxi","award":["2021TD-08"],"award-info":[{"award-number":["2021TD-08"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1007\/s00371-024-03628-4","type":"journal-article","created":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T04:01:42Z","timestamp":1727928102000},"page":"3695-3717","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Progressive Crowd Enhancement De-Background Network for crowd counting"],"prefix":"10.1007","volume":"41","author":[{"given":"Lin","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengping","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"issue":"5","key":"3628_CR1","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, A.B.: Beyond counting: comparisons of density maps for crowd analysis tasks\u2014counting, detection, and tracking. IEEE Trans. Circuits Syst. Video Technol. 29(5), 1408\u20131422 (2018). https:\/\/doi.org\/10.1109\/TCSVT.2018.2837153","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3628_CR2","doi-asserted-by":"publisher","unstructured":"Li, Y., Zhang, X., Chen, D.: CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1091-1100 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00120","DOI":"10.1109\/CVPR.2018.00120"},{"key":"3628_CR3","doi-asserted-by":"publisher","unstructured":"Cao, X., Wang, Z., Zhao, Y., Su, F.: Scale aggregation network for accurate and efficient crowd counting. In: Proceedings of the European conference on computer vision, pp. 734-750 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_45","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"3628_CR4","doi-asserted-by":"publisher","unstructured":"Miao, Y., Lin, Z., Ding, G., Han, J.: Shallow feature based dense attention network for crowd counting. In: Proceedings of the AAAI conference on artificial intelligence, pp. 11765-11772 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6848","DOI":"10.1609\/aaai.v34i07.6848"},{"key":"3628_CR5","doi-asserted-by":"publisher","unstructured":"Zhao, M., Zhang, J., Zhang, C., Zhang, W.: Leveraging heterogeneous auxiliary tasks to assist crowd counting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 12736-12745 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01302","DOI":"10.1109\/CVPR.2019.01302"},{"key":"3628_CR6","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1016\/j.ins.2022.01.046","volume":"591","author":"F Wang","year":"2022","unstructured":"Wang, F., Sang, J., Wu, Z., Liu, Q., Sang, N.: Hybrid attention network based on progressive embedding scale-context for crowd counting. Inf. Sci. 591, 306\u2013318 (2022). https:\/\/doi.org\/10.1016\/j.ins.2022.01.046","journal-title":"Inf. Sci."},{"key":"3628_CR7","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"3628_CR8","doi-asserted-by":"publisher","first-page":"1395","DOI":"10.1109\/TIP.2020.3043122","volume":"30","author":"Y Yang","year":"2021","unstructured":"Yang, Y., Li, G., Du, D., Huang, Q., Sebe, N.: Embedding perspective analysis into multi-column convolutional neural network for crowd counting. IEEE Trans. Image Process. 30, 1395\u20131407 (2021). https:\/\/doi.org\/10.1109\/TIP.2020.3043122","journal-title":"IEEE Trans. Image Process."},{"key":"3628_CR9","doi-asserted-by":"publisher","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2881-2890 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.660","DOI":"10.1109\/CVPR.2017.660"},{"key":"3628_CR10","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp. 1026-1034 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.123","DOI":"10.1109\/ICCV.2015.123"},{"key":"3628_CR11","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-image crowd counting via multi-column convolutional neural network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 589-597 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.70","DOI":"10.1109\/CVPR.2016.70"},{"issue":"1","key":"3628_CR12","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1109\/TII.2021.3085669","volume":"18","author":"J Li","year":"2022","unstructured":"Li, J., Chen, J., Sheng, B., Li, P., Yang, P., Feng, D.D., Qi, J.: Automatic detection and classification system of domestic waste via multimodel cascaded convolutional neural network. IEEE Trans. Ind. Inform. 18(1), 163\u2013173 (2022). https:\/\/doi.org\/10.1109\/TII.2021.3085669","journal-title":"IEEE Trans. Ind. Inform."},{"key":"3628_CR13","doi-asserted-by":"publisher","unstructured":"Sindagi, V.A., Patel, V.M.: Multi-level bottom-top and top-bottom feature fusion for crowd counting. In: Proceedings of the IEEE international conference on computer vision, pp. 1002-1012 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00109","DOI":"10.1109\/ICCV.2019.00109"},{"key":"3628_CR14","doi-asserted-by":"publisher","unstructured":"Liu, L., Lu, H., Zou, H., Xiong, H., Cao, Z., Shen, C.: Weighing counts: sequential crowd counting by reinforcement learning. In: Proceedings of the European conference on computer vision, pp. 164-181 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_10","DOI":"10.1007\/978-3-030-58607-2_10"},{"key":"3628_CR15","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.: Removing background interference for crowd counting via de-background detail convolutional network. Neurocomputing 332, 360\u2013371 (2019). https:\/\/doi.org\/10.1016\/j.neucom.2018.12.047","journal-title":"Neurocomputing"},{"issue":"8","key":"3628_CR16","doi-asserted-by":"publisher","first-page":"2739","DOI":"10.1109\/TPAMI.2020.2974830","volume":"43","author":"DB Sam","year":"2021","unstructured":"Sam, D.B., Peri, S.V., Sundararaman, M.N., Kamath, A., Babu, R.V.: Locate, size, and count: accurately resolving people in dense crowds via detection. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2739\u20132751 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.2974830","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3628_CR17","doi-asserted-by":"publisher","unstructured":"Yang, Y., Li, G., Wu, Z., Su, L., Huang, Q., Sebe, N.: Reverse perspective network for perspective-aware object counting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4373-4382 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00443","DOI":"10.1109\/CVPR42600.2020.00443"},{"key":"3628_CR18","doi-asserted-by":"publisher","unstructured":"Luo, A., Yang, F., Li, X., Nie, D., Jiao, Z., Zhou, S., Cheng, H.: Hybrid graph neural networks for crowd counting. In: Proceedings of the AAAI conference on artificial intelligence, pp. 11693-11700 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6839","DOI":"10.1609\/aaai.v34i07.6839"},{"key":"3628_CR19","doi-asserted-by":"publisher","unstructured":"Oh, M.H., Olsen, P., Ramamurthy, K.N.: Crowd counting with decomposed uncertainty. In: Proceedings of the AAAI conference on artificial intelligence, pp. 11799-11806 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6852","DOI":"10.1609\/aaai.v34i07.6852"},{"issue":"7","key":"3628_CR20","doi-asserted-by":"publisher","first-page":"3602","DOI":"10.1109\/TPAMI.2021.3056518","volume":"44","author":"JT Zhou","year":"2022","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. 44(7), 3602\u20133613 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3056518","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3628_CR21","doi-asserted-by":"crossref","unstructured":"Liu, C., Lu, H., Cao, Z., Liu, T.: Point-query quadtree for crowd counting, localization, and more. In: Proceedings of the IEEE international conference on computer vision, pp. 1676-1685 (2023)","DOI":"10.1109\/ICCV51070.2023.00161"},{"key":"3628_CR22","doi-asserted-by":"publisher","unstructured":"Abousamra, S., Hoai, M., Samaras, D., Chen, C.: Localization in the crowd with topological constraints. In: Proceedings of the AAAI conference on artificial intelligence, pp. 872-881 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i2.16170","DOI":"10.1609\/aaai.v35i2.16170"},{"issue":"2","key":"3628_CR23","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2050","volume":"34","author":"J Chen","year":"2023","unstructured":"Chen, J., Yuan, H., Zhang, Y., He, R., Liang, J.: DCR-Net: dilated convolutional residual network for fashion image retrieval. Comput. Animat. Virtual Worlds. 34(2), e2050 (2023). https:\/\/doi.org\/10.1002\/cav.2050","journal-title":"Comput. Animat. Virtual Worlds."},{"key":"3628_CR24","doi-asserted-by":"publisher","unstructured":"Wan, J., Liu, Z., Chan, A.B.: A generalized loss function for crowd counting and localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1974-1983 (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00201","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"3628_CR25","doi-asserted-by":"publisher","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: Proceedings of the European conference on computer vision, pp. 532-546 (2018). https:\/\/doi.org\/10.1007\/978-3-030-01216-8_33","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"3628_CR26","doi-asserted-by":"publisher","unstructured":"Yan, Z., Yuan, Y., Zuo, W., Tan, X., Wang, Y., Wen, S., Ding, E.: Perspective-guided convolution networks for crowd counting. In: Proceedings of the IEEE international conference on computer vision, pp. 952-961 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00104","DOI":"10.1109\/ICCV.2019.00104"},{"key":"3628_CR27","doi-asserted-by":"publisher","unstructured":"Hu, Y., Jiang, X., Liu, X., Zhang, B., Han, J., Cao, X., Doermann, D.: NAS-Count: Counting-by-density with neural architecture search. In: Proceedings of the European conference on computer vision, pp. 747-766 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_45","DOI":"10.1007\/978-3-030-58542-6_45"},{"issue":"6","key":"3628_CR28","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3445-y","volume":"65","author":"D Liang","year":"2022","unstructured":"Liang, D., Chen, X., Xu, W., Zhou, Y., Bai, X.: Transcrowd:weakly-supervised crowd counting with transformers. Sci. China-Inf. Sci. 65(6), 160104 (2022). https:\/\/doi.org\/10.1007\/s11432-021-3445-y","journal-title":"Sci. China-Inf. Sci."},{"issue":"3","key":"3628_CR29","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1109\/TPAMI.2020.3022878","volume":"44","author":"J Wan","year":"2022","unstructured":"Wan, J., Wang, Q., Chan, A.B.: Kernel-based density map generation for dense object counting. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1357\u20131370 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2020.3022878","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3628_CR30","doi-asserted-by":"publisher","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, pp. 2547-2554 (2013). https:\/\/doi.org\/10.1109\/10.1109\/CVPR.2013.329","DOI":"10.1109\/10.1109\/CVPR.2013.329"},{"key":"3628_CR31","doi-asserted-by":"publisher","unstructured":"Cheng, Z.Q., Dai, Q., Li, H., Song, J., Wu, X., Hauptmann, A.G.: Rethinking spatial invariance of convolutional networks for object counting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 19606-19616 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01902","DOI":"10.1109\/CVPR52688.2022.01902"},{"key":"3628_CR32","unstructured":"Wan, J., Chan, A.: Modeling noisy annotations for crowd counting. In: advances in neural information processing systems, pp. 3386-3396 (2020)"},{"issue":"6","key":"3628_CR33","doi-asserted-by":"publisher","first-page":"2141","DOI":"10.1109\/TPAMI.2020.3013269","volume":"43","author":"Q Wang","year":"2021","unstructured":"Wang, Q., Gao, J., Lin, W., Li, X.: NWPU-Crowd: a large-scale benchmark for crowd counting and localization. IEEE Trans. Pattern Anal. Mach. Intell. 43(6), 2141\u20132149 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.3013269","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3628_CR34","doi-asserted-by":"publisher","first-page":"2671","DOI":"10.1007\/s00371-022-02485-3","volume":"39","author":"B Li","year":"2023","unstructured":"Li, B., Zhang, Y., Xu, H., Yin, B.: CCST: crowd counting with swin transformer. Vis. Comput. 39, 2671\u20132682 (2023). https:\/\/doi.org\/10.1007\/s00371-022-02485-3","journal-title":"Vis. Comput."},{"key":"3628_CR35","doi-asserted-by":"publisher","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. 6141-6150 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00624","DOI":"10.1109\/ICCV.2019.00624"},{"issue":"10","key":"3628_CR36","doi-asserted-by":"publisher","first-page":"3486","DOI":"10.1109\/TCSVT.2019.2919139","volume":"30","author":"J Gao","year":"2020","unstructured":"Gao, J., Wang, Q., Li, X.: PCC Net: perspective crowd counting via spatial convolutional network. IEEE Trans. Circuits Syst. Video Technol. 30(10), 3486\u20133498 (2020). https:\/\/doi.org\/10.1109\/TCSVT.2019.2919139","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3628_CR37","doi-asserted-by":"publisher","unstructured":"Liu, W., Salzmann, M., Fua, P.: Context-aware crowd counting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5094-5103 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00524","DOI":"10.1109\/CVPR.2019.00524"},{"key":"3628_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). https:\/\/doi.org\/10.1016\/j.neucom.2021.04.045","journal-title":"Neurocomputing"},{"key":"3628_CR39","doi-asserted-by":"publisher","unstructured":"Ma, Z., Wei, X., Hong, X., Lin, H., Qiu, Y., Gong, Y.: Learning to count via unbalanced optimal transport. In: Proceedings of the AAAI conference on artificial intelligence, pp. 2319-2327 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i3.16332","DOI":"10.1609\/aaai.v35i3.16332"},{"key":"3628_CR40","doi-asserted-by":"publisher","unstructured":"Li, M., Zhang, Z., Huang, K., Tan, T.: Estimating the number of people in crowded scenes by mid based foreground segmentation and head-shoulder detection. In: 19th international conference on pattern recognition, pp. 1-4 (2008). https:\/\/doi.org\/10.1109\/ICPR.2008.4761705","DOI":"10.1109\/ICPR.2008.4761705"},{"key":"3628_CR41","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, M.J.: Robust real-time face detection. Int. J. Comput. Vis. 57, 137\u2013154 (2004). https:\/\/doi.org\/10.1023\/B:VISI.0000013087.49260.fb","journal-title":"Int. J. Comput. Vis."},{"key":"3628_CR42","doi-asserted-by":"publisher","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 886-893 (2005). https:\/\/doi.org\/10.1109\/CVPR.2005.177","DOI":"10.1109\/CVPR.2005.177"},{"key":"3628_CR43","doi-asserted-by":"publisher","unstructured":"Chan, A.B., Liang, Z.S.J., Vasconcelos, N.: Privacy preserving crowd monitoring: Counting people without people models or tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1-7 (2008). https:\/\/doi.org\/10.1109\/CVPR.2008.4587569","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"3628_CR44","unstructured":"Lempitsky, V., Zisserman, A.: Learning to count objects in images. In: advances in neural information processing systems, pp. 1324\u20131332 (2010)"},{"key":"3628_CR45","doi-asserted-by":"publisher","unstructured":"Pham, V.Q., Kozakaya, T., Yamaguchi, O., Okada, R.: 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. 3253-3261 (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.372","DOI":"10.1109\/ICCV.2015.372"},{"key":"3628_CR46","doi-asserted-by":"publisher","unstructured":"Shu, W., Wan, J., Tan, K.C., Kwong, S., Chan, A.B.: Crowd counting in the frequency domain. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 19586-19595 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.01900","DOI":"10.1109\/CVPR52688.2022.01900"},{"key":"3628_CR47","doi-asserted-by":"publisher","unstructured":"Liang, D., Xu, W., Bai, X.: An end-to-end transformer model for crowd localization. In: proceedings of the European conference on computer vision, pp. 38-54 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_3","DOI":"10.1007\/978-3-031-19769-7_3"},{"key":"3628_CR48","doi-asserted-by":"publisher","unstructured":"Sam, D.B., Surya, S., Babu, R.V.: Switching convolutional neural network for crowd counting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4031-4039 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.429","DOI":"10.1109\/CVPR.2017.429"},{"key":"3628_CR49","doi-asserted-by":"publisher","unstructured":"Wang, Y., Hou, X., Chau, L.P.: Dense point prediction: a simple baseline for crowd counting and localization. In: Proceedings of the IEEE international conference on multimedia & expo workshops, pp. 1-6 (2021). https:\/\/doi.org\/10.1109\/ICMEW53276.2021.9455954","DOI":"10.1109\/ICMEW53276.2021.9455954"},{"key":"3628_CR50","unstructured":"Wang, B., Liu, H., Samaras, D., Nguyen, M.H.: Distribution matching for crowd counting. In: Advances in neural information processing systems, pp. 1595-1607 (2020)"},{"key":"3628_CR51","doi-asserted-by":"publisher","unstructured":"Jiang, X., Zhang, L., Xu, M., Zhang, T., Lv, P., Zhou, B., Yang, X., Pang, Y.: Attention scaling for crowd counting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4705-4714 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00476","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"3628_CR52","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1109\/TMM.2020.2980945","volume":"23","author":"X Jiang","year":"2020","unstructured":"Jiang, X., Zhang, L., Zhang, T., Lv, P., Zhou, B., Pang, Y., Xu, M., Xu, C.: Density-aware multi-task learning for crowd counting. IEEE Trans. Multimedia 23, 443\u2013453 (2020). https:\/\/doi.org\/10.1109\/TMM.2020.2980945","journal-title":"IEEE Trans. Multimedia"},{"key":"3628_CR53","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109944","volume":"257","author":"H Li","year":"2022","unstructured":"Li, H., Zhang, S., Kong, W.: Learning the cross-modal discriminative feature representation for RGB-T crowd counting. Knowledge-Based Syst. 257, 109944 (2022). https:\/\/doi.org\/10.1016\/j.knosys.2022.109944","journal-title":"Knowledge-Based Syst."},{"key":"3628_CR54","doi-asserted-by":"publisher","unstructured":"Gong, S., Zhang, S., Yang, J., Dai, D., Schiele, B.: Bi-level alignment for cross-domain crowd counting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7532-7540 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00739","DOI":"10.1109\/CVPR52688.2022.00739"},{"key":"3628_CR55","doi-asserted-by":"publisher","unstructured":"Wu, Z., Sang, J., Shi, Y., Liu, Q., Sang, N., Liu, X.: CRANet: Cascade residual attention network for crowd counting. In: Proceedings of the IEEE international conference on multimedia and expo, pp. 1-6 (2021). https:\/\/doi.org\/10.1109\/ICME51207.2021.9428236","DOI":"10.1109\/ICME51207.2021.9428236"},{"issue":"2","key":"3628_CR56","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/s11263-021-01542-z","volume":"130","author":"C Xu","year":"2022","unstructured":"Xu, C., Liang, D., Xu, Y., Bai, S., Zhan, W., Bai, X., Tomizuka, M.: Autoscale: learning to scale for crowd counting. Int. J. Comput. Vis. 130(2), 405\u2013434 (2022). https:\/\/doi.org\/10.1007\/s11263-021-01542-z","journal-title":"Int. J. Comput. Vis."},{"key":"3628_CR57","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). https:\/\/doi.org\/10.1016\/j.neucom.2019.08.018","journal-title":"Neurocomputing"},{"key":"3628_CR58","doi-asserted-by":"publisher","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. 1774-1783 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00186","DOI":"10.1109\/ICCV.2019.00186"},{"key":"3628_CR59","doi-asserted-by":"publisher","unstructured":"Dai, F., Liu, H., Ma, Y., Zhang, X., Zhao, Q.: Dense scale network for crowd counting. In: Proceedings of the international conference on multimedia retrieval, pp. 64-72 (2021). https:\/\/doi.org\/10.1145\/3460426.3463628","DOI":"10.1145\/3460426.3463628"},{"key":"3628_CR60","unstructured":"Tran, N.H., Huy, T.D., Duong, S.T., Nguyen, P., Hung, D.H., Nguyen, C.D.T., Bui, T., Truong, S.Q.: Improving local features with relevant spatial information by vision transformer for crowd counting. In: Proceedings of the British machine vision conference, 2022"},{"key":"3628_CR61","doi-asserted-by":"publisher","unstructured":"Rong, L., Li, C.: Coarse- and fine-grained attention network with background-aware loss for crowd density map estimation. In: Proceedings of the IEEE winter conference on applications of computer vision, pp. 3675-3684 (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00372","DOI":"10.1109\/WACV48630.2021.00372"},{"key":"3628_CR62","doi-asserted-by":"publisher","unstructured":"Bai, S., He, Z., Qiao, Y., Hu, H., Wu, W., Yan, J.: Adaptive dilated network with self-correction supervision for counting. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4593-4602 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00465","DOI":"10.1109\/CVPR42600.2020.00465"},{"key":"3628_CR63","doi-asserted-by":"publisher","unstructured":"Liu, X., Yang, J., Ding, W., Wang, T., Wang, Z., Xiong, J.: Adaptive mixture regression network with local counting map for crowd counting. In: Proceedings of the European conference on computer vision, pp. 241-257 (2020). https:\/\/doi.org\/10.1007\/978-3-030-58586-0_15","DOI":"10.1007\/978-3-030-58586-0_15"},{"key":"3628_CR64","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: Efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2023). https:\/\/doi.org\/10.1109\/TMM.2021.3120873","journal-title":"IEEE Trans. Multimedia"},{"issue":"4","key":"3628_CR65","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2018","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2018). https:\/\/doi.org\/10.1109\/TPAMI.2017.2699184","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3628_CR66","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: Proceedings of the international conference on learning representations, pp. 1-12 (2020)"},{"key":"3628_CR67","doi-asserted-by":"publisher","unstructured":"Liu, Y., Shi, M., Zhao, Q., Wang, X.: Point in, Box Out: Beyond counting persons in crowds. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6462-6471 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00663","DOI":"10.1109\/CVPR.2019.00663"},{"key":"3628_CR68","doi-asserted-by":"publisher","unstructured":"Liu, N., Long, Y., Zou, C., Niu, Q., Pan, L., Wu, H.: ADCrowdNet: An attention-injective deformable convolutional network for crowd understanding. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3220-3229 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00334","DOI":"10.1109\/CVPR.2019.00334"},{"key":"3628_CR69","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1007\/s44196-021-00016-x","volume":"14","author":"SD Khan","year":"2021","unstructured":"Khan, S.D., Salih, Y., Zafar, B., Noorwali, A.: A deep-fusion network for crowd counting in high-density crowded scenes. Int. J. Comput. Intell. Syst. 14, 168 (2021). https:\/\/doi.org\/10.1007\/s44196-021-00016-x","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"3628_CR70","doi-asserted-by":"publisher","first-page":"3051","DOI":"10.1007\/s13369-020-04990-w","volume":"46","author":"SD Khan","year":"2021","unstructured":"Khan, S.D., Basalamah, S.: Sparse to dense scale prediction for crowd couting in high density crowds. Arab. J. Sci. Eng. 46, 3051\u20133065 (2021). https:\/\/doi.org\/10.1007\/s13369-020-04990-w","journal-title":"Arab. J. Sci. Eng."},{"key":"3628_CR71","doi-asserted-by":"publisher","first-page":"71576","DOI":"10.1109\/ACCESS.2019.2918650","volume":"7","author":"S Basalamah","year":"2019","unstructured":"Basalamah, S., Khan, S.D., Ullah, H.: Scale driven convolutional neural network model for people counting and localization in crowd scenes. IEEE Access. 7, 71576\u201371584 (2019). https:\/\/doi.org\/10.1109\/ACCESS.2019.2918650","journal-title":"IEEE Access."},{"key":"3628_CR72","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). https:\/\/doi.org\/10.1007\/s00371-020-01974-7","journal-title":"Vis. Comput."},{"key":"3628_CR73","doi-asserted-by":"publisher","first-page":"2594","DOI":"10.1109\/TPAMI.2020.3035969","volume":"44","author":"VA Sindagi","year":"2020","unstructured":"Sindagi, V.A., Yasarla, R., Patel, V.M.: JHU-CROWD++: large-scale crowd counting dataset and a benchmark method. IEEE Trans. Pattern Anal. Mach. Intell. 44, 2594\u20132609 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2020.3035969","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3628_CR74","doi-asserted-by":"publisher","first-page":"2862","DOI":"10.1109\/TIP.2021.3055631","volume":"30","author":"J Cheng","year":"2021","unstructured":"Cheng, J., Xiong, H., Cao, Z., Lu, H.: Decoupled two-stage crowd counting and beyond. IEEE Trans. Image Process. 30, 2862\u20132875 (2021). https:\/\/doi.org\/10.1109\/TIP.2021.3055631","journal-title":"IEEE Trans. Image Process."},{"issue":"12","key":"3628_CR75","doi-asserted-by":"publisher","first-page":"24540","DOI":"10.1109\/TITS.2022.3203385","volume":"23","author":"W Zhou","year":"2022","unstructured":"Zhou, W., Pan, Y., Lei, J., Ye, L., Yu, L.: DEFNet: dual-branch enhanced feature fusion network for RGB-T crowd counting. IEEE Trans. Intell. Transp. Syst. 23(12), 24540\u201324549 (2022). https:\/\/doi.org\/10.1109\/TITS.2022.3203385","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"3628_CR76","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1007\/s13735-021-00220-7","volume":"10","author":"SK Tripathy","year":"2021","unstructured":"Tripathy, S.K., Srivastava, R.: AMS-CNN: attentive multi-stream CNN for video-based crowd counting. Int J Multimed Info Retr. 10, 239\u2013254 (2021). https:\/\/doi.org\/10.1007\/s13735-021-00220-7","journal-title":"Int J Multimed Info Retr."},{"key":"3628_CR77","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-024-09681-4","author":"SK Tripathy","year":"2024","unstructured":"Tripathy, S.K., Srivastava, S., Bajaj, D., Srivastava, R.: A novel cascaded deep architecture with weak-supervision for video crowd counting and density estimation. Soft. Comput. (2024). https:\/\/doi.org\/10.1007\/s00500-024-09681-4","journal-title":"Soft. Comput."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03628-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03628-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03628-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T10:21:00Z","timestamp":1744798860000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03628-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,3]]},"references-count":77,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["3628"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03628-4","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2024,10,3]]},"assertion":[{"value":"29 August 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2024","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 declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}