{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T03:41:40Z","timestamp":1792035700869,"version":"4.4.0"},"reference-count":97,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T00:00:00Z","timestamp":1707436800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T00:00:00Z","timestamp":1707436800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s11263-024-01990-3","type":"journal-article","created":{"date-parts":[[2024,2,9]],"date-time":"2024-02-09T17:04:34Z","timestamp":1707498274000},"page":"2600-2617","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Focus for Free in Density-Based Counting"],"prefix":"10.1007","volume":"132","author":[{"given":"Zenglin","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pascal","family":"Mettes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cees G. M.","family":"Snoek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,9]]},"reference":[{"key":"1990_CR1","doi-asserted-by":"crossref","unstructured":"Babu\u00a0Sam, D., Sajjan, N.N., Venkatesh\u00a0Babu, R., & Srinivasan, M. (2018). Divide and grow: Capturing huge diversity in crowd images with incrementally growing CNN. In CVPR.","DOI":"10.1109\/CVPR.2018.00381"},{"key":"1990_CR2","doi-asserted-by":"crossref","unstructured":"Bai, S., He, Z., Qiao, Y., Hu, H., Wu, W., & Yan, J. (2020). Adaptive dilated network with self-correction supervision for counting. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00465"},{"key":"1990_CR3","doi-asserted-by":"crossref","unstructured":"Brostow, G.J., & Cipolla, R. (2006). Unsupervised bayesian detection of independent motion in crowds. In CVPR.","DOI":"10.1109\/CVPR.2006.320"},{"key":"1990_CR4","doi-asserted-by":"crossref","unstructured":"Cao X, Wang, Z., Zhao, Y., & Su, F. (2018). Scale aggregation network for accurate and efficient crowd counting. In ECCV.","DOI":"10.1007\/978-3-030-01228-1_45"},{"key":"1990_CR5","doi-asserted-by":"crossref","unstructured":"Chan, A.B., & Vasconcelos, N. (2009). Bayesian poisson regression for crowd counting. In ICCV, pp 545\u2013551.","DOI":"10.1109\/ICCV.2009.5459191"},{"issue":"4","key":"1990_CR6","doi-asserted-by":"publisher","first-page":"2160","DOI":"10.1109\/TIP.2011.2172800","volume":"21","author":"AB Chan","year":"2011","unstructured":"Chan, A. B., & Vasconcelos, N. (2011). Counting people with low-level features and Bayesian regression. IEEE Transactions on Image Processing, 21(4), 2160\u20132177.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1990_CR7","doi-asserted-by":"crossref","unstructured":"Chan, A.B., Liang, Z.S.J., &Vasconcelos, N. (2008). Privacy preserving crowd monitoring: Counting people without people models or tracking. In CVPR.","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"1990_CR8","doi-asserted-by":"crossref","unstructured":"Chen, K., Loy, C.C., Gong, S., & Xiang, T. (2012) Feature mining for localised crowd counting. In BMVC.","DOI":"10.5244\/C.26.21"},{"key":"1990_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L., Zhang, H., Xiao, J., Nie, L., Shao, J., Liu, W., Chua, T.S. (2017). Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning. In CVPR.","DOI":"10.1109\/CVPR.2017.667"},{"key":"1990_CR10","doi-asserted-by":"crossref","unstructured":"Chen, S., Shi, Z., Mettes, P., & Snoek, C.G. (2021). Social fabric: Tubelet compositions for video relation detection. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01323"},{"key":"1990_CR11","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. (2021). Decoupled two-stage crowd counting and beyond. IEEE Transactions on Image Processing, 30, 2862\u20132875.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1990_CR12","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Li, J.X., Dai, Q., Wu, X., & Hauptmann, A.G. (2019a). Learning spatial awareness to improve crowd counting. In ICCV.","DOI":"10.1109\/ICCV.2019.00625"},{"key":"1990_CR13","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Li, J.X., Dai, Q., Wu, X., He, J.Y., & Hauptmann, A, (2019b), Improving the learning of multi-column convolutional neural network for crowd counting. In ACM MM.","DOI":"10.1145\/3343031.3350898"},{"key":"1990_CR14","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Dai, Q., Li, H., Song, J., Wu, X., & Hauptmann, A.G. (2022). Rethinking spatial invariance of convolutional networks for object counting. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01902"},{"key":"1990_CR15","unstructured":"DeVries, T., & Taylor, G.W. (2017). Improved regularization of convolutional neural networks with cutout. arXiv:1708.04552"},{"key":"1990_CR16","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., & Uszkoreit, J., (2020) An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929"},{"key":"1990_CR17","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.neucom.2022.09.113","volume":"513","author":"J Gao","year":"2022","unstructured":"Gao, J., Gong, M., & Li, X. (2022). Congested crowd instance localization with dilated convolutional swin transformer. Neurocomputing, 513, 94\u2013103.","journal-title":"Neurocomputing"},{"key":"1990_CR18","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Cui, Y., Srinivas, A., Qian, R., Lin, T.Y., Cubuk, E.D., Le, Q.V., & Zoph, B. (2021). Simple copy-paste is a strong data augmentation method for instance segmentation. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"1990_CR19","doi-asserted-by":"crossref","unstructured":"Guerrero-G\u00f3mez-Olmedo, R., Torre-Jim\u00e9nez, B., L\u00f3pez-Sastre, R., Maldonado-Basc\u00f3n, S., Onoro-Rubio, D. (2015). Extremely overlapping vehicle counting. In IbPRIA.","DOI":"10.1007\/978-3-319-19390-8_48"},{"key":"1990_CR20","unstructured":"Hinton, G., Vinyals, O., & Dean, J. (2015). Distilling the knowledge in a neural network. arXiv:1503.02531"},{"key":"1990_CR21","doi-asserted-by":"crossref","unstructured":"Hu. J., Shen, L., & Sun, G. (2018). Squeeze-and-excitation networks. In CVPR.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1990_CR22","doi-asserted-by":"crossref","unstructured":"Hu, Y., Jiang, X., Liu, X., Zhang, B., Han, J., Cao, X., & Doermann, D. (2020). Nas-count: Counting-by-density with neural architecture search. In ECCV.","DOI":"10.1007\/978-3-030-58542-6_45"},{"key":"1990_CR23","doi-asserted-by":"crossref","unstructured":"Huang, S., Li, X., Cheng, Z.Q., Zhang, Z., & Hauptmann, A. (2020). Stacked pooling for boosting scale invariance of crowd counting. In ICASSP.","DOI":"10.1109\/ICASSP40776.2020.9053070"},{"key":"1990_CR24","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 CVPR","DOI":"10.1109\/CVPR.2013.329"},{"key":"1990_CR25","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 ECCV.","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"1990_CR26","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 CVPR.","DOI":"10.1109\/CVPR.2019.00629"},{"key":"1990_CR27","doi-asserted-by":"crossref","unstructured":"Jiang, X., Zhang, L., Xu, M., Zhang, T., Lv, P., Zhou, B., Yang, X., & Pang, Y. (2020a). Attention scaling for crowd counting. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"1990_CR28","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. (2020). Density-aware multi-task learning for crowd counting. IEEE Transactions on Multimedia, 23, 443\u2013453.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1990_CR29","doi-asserted-by":"publisher","first-page":"2897","DOI":"10.1007\/s11263-020-01345-8","volume":"128","author":"D Kang","year":"2020","unstructured":"Kang, D., Dhar, D., & Chan, A. (2020). Incorporating side information by adaptive convolution. International Journal of Computer Vision, 128, 2897\u20132918.","journal-title":"International Journal of Computer Vision"},{"key":"1990_CR30","doi-asserted-by":"crossref","unstructured":"Leibe, B., Seemann, E., & Schiele, B. (2005). Pedestrian detection in crowded scenes. In CVPR.","DOI":"10.1109\/CVPR.2005.272"},{"key":"1990_CR31","unstructured":"Lempitsky, V., & Zisserman, A. (2010). Learning to count objects in images. In NeurIPS."},{"key":"1990_CR32","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: ICPR, pp 1\u20134","DOI":"10.1109\/ICPR.2008.4761705"},{"key":"1990_CR33","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, X., & Chen, D. (2018). Csrnet: Dilated convolutional neural networks for understanding the highly congested scenes. In CVPR.","DOI":"10.1109\/CVPR.2018.00120"},{"issue":"6","key":"1990_CR34","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. (2022). Transcrowd: Weakly-supervised crowd counting with transformers. SCIENCE CHINA Information Sciences, 65(6), 160104.","journal-title":"SCIENCE CHINA Information Sciences"},{"key":"1990_CR35","doi-asserted-by":"publisher","first-page":"6040","DOI":"10.1109\/TMM.2022.3203870","volume":"25","author":"D Liang","year":"2022","unstructured":"Liang, D., Xu, W., Zhu, Y., & Zhou, Y. (2022). Focal inverse distance transform maps for crowd localization. IEEE Transactions on Multimedia, 25, 6040\u20136052.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1990_CR36","doi-asserted-by":"crossref","unstructured":"Lin, H., Ma, Z., Ji, R., Wang, Y., & Hong, X. (2022). Boosting crowd counting via multifaceted attention. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01901"},{"issue":"6","key":"1990_CR37","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1109\/3468.983420","volume":"31","author":"SF Lin","year":"2001","unstructured":"Lin, S. F., Chen, J. Y., & Chao, H. X. (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":"1990_CR38","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P. (2017). Focal loss for dense object detection. In ICCV.","DOI":"10.1109\/ICCV.2017.324"},{"key":"1990_CR39","doi-asserted-by":"crossref","unstructured":"Liu, J., Gao, C., Meng, D., Hauptmann, A.G. (2018a). Decidenet: Counting varying density crowds through attention guided detection and density estimation. In CVPR.","DOI":"10.1109\/CVPR.2018.00545"},{"key":"1990_CR40","doi-asserted-by":"crossref","unstructured":"Liu, L., Wang, H., Li, G., Ouyang, W., & Lin, L. (2018b). Crowd counting using deep recurrent spatial-aware network. In IJCAI.","DOI":"10.24963\/ijcai.2018\/118"},{"key":"1990_CR41","doi-asserted-by":"crossref","unstructured":"Liu, N., Long, Y., Zou, C., Niu, Q., Pan, L., Wu, H. (2019a). Adcrowdnet: An attention-injective deformable convolutional network for crowd understanding. In CVPR.","DOI":"10.1109\/CVPR.2019.00334"},{"key":"1990_CR42","doi-asserted-by":"crossref","unstructured":"Liu, W., Salzmann, M., Fua, P. (2019b). Context-aware crowd counting. In CVPR.","DOI":"10.1109\/CVPR.2019.00524"},{"key":"1990_CR43","doi-asserted-by":"crossref","unstructured":"Liu, X., van\u00a0de Weijer, J., Bagdanov, A.D. (2018c). Leveraging unlabeled data for crowd counting by learning to rank. In CVPR.","DOI":"10.1109\/CVPR.2018.00799"},{"key":"1990_CR44","doi-asserted-by":"crossref","unstructured":"Liu, X., Yang, J., Ding, W., Wang, T., Wang, Z., & Xiong, J. (2020). Adaptive mixture regression network with local counting map for crowd counting. In ECCV.","DOI":"10.1007\/978-3-030-58586-0_15"},{"key":"1990_CR45","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, G., Han, Z., Zhang, W., Yang, Y., Huang, Q., Sebe, N. (2021). Exploiting sample correlation for crowd counting with multi-expert network. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00320"},{"issue":"1","key":"1990_CR46","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/s11263-021-01539-8","volume":"130","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Cheng, M. M., Fan, D. P., Zhang, L., Bian, J. W., & Tao, D. (2022). Semantic edge detection with diverse deep supervision. International Journal of Computer Vision, 130(1), 179\u2013198.","journal-title":"International Journal of Computer Vision"},{"key":"1990_CR47","doi-asserted-by":"crossref","unstructured":"Ma, Z., Wei, X., Hong, X., & Gong, Y. (2019). Bayesian loss for crowd count estimation with point supervision. In: ICCV.","DOI":"10.1109\/ICCV.2019.00624"},{"key":"1990_CR48","doi-asserted-by":"crossref","unstructured":"Ma, Z., Wei, X., Hong, X., & Gong, Y. (2020) Learning scales from points: A scale-aware probabilistic model for crowd counting. In ACM MM.","DOI":"10.1145\/3394171.3413642"},{"key":"1990_CR49","doi-asserted-by":"crossref","unstructured":"Ma, Z., Hong, X., Wei, X., Qiu, Y., Gong, Y. (2021). Towards a universal model for cross-dataset crowd counting. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00319"},{"key":"1990_CR50","doi-asserted-by":"publisher","first-page":"8199","DOI":"10.1109\/TIP.2020.3009030","volume":"29","author":"H Mo","year":"2020","unstructured":"Mo, H., Ren, W., Xiong, Y., Pan, X., Zhou, Z., Cao, X., & Wu, W. (2020). Background noise filtering and distribution dividing for crowd counting. IEEE Transactions on Image Processing, 29, 8199\u20138212.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1990_CR51","doi-asserted-by":"crossref","unstructured":"Modolo, D., Shuai, B., Varior, R.R., & Tighe, J. (2021). Understanding the impact of mistakes on background regions in crowd counting. In WACV.","DOI":"10.1109\/WACV48630.2021.00169"},{"key":"1990_CR52","doi-asserted-by":"crossref","unstructured":"Onoro-Rubio, D., & L\u00f3pez-Sastre, R.J. (2016) Towards perspective-free object counting with deep learning. In ECCV.","DOI":"10.1007\/978-3-319-46478-7_38"},{"issue":"5\u20136","key":"1990_CR53","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1561\/2200000073","volume":"11","author":"G Peyr\u00e9","year":"2019","unstructured":"Peyr\u00e9, G., Cuturi, M., et al. (2019). Computational optimal transport: With applications to data science. Foundations and Trends\u00ae in Machine Learning, 11(5\u20136), 355\u2013607.","journal-title":"Foundations and Trends\u00ae in Machine Learning"},{"key":"1990_CR54","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. In ICCV.","DOI":"10.1109\/ICCV.2015.372"},{"key":"1990_CR55","unstructured":"Qian, Y., Zhang, L., Hong, X., Donovan, C.R., & Arandjelovic, O. (2022). Segmentation assisted u-shaped multi-scale transformer for crowd counting. In BMVC."},{"key":"1990_CR56","doi-asserted-by":"crossref","unstructured":"Rabaud, V., Belongie, S. (2006). Counting crowded moving objects. In CVPR.","DOI":"10.1109\/CVPR.2006.92"},{"key":"1990_CR57","doi-asserted-by":"crossref","unstructured":"Ranjan, V., Le, H., & Hoai, M. (2018). Iterative crowd counting. In ECCV","DOI":"10.1007\/978-3-030-01234-2_17"},{"key":"1990_CR58","doi-asserted-by":"crossref","unstructured":"Rong, L., & Li, C. (2021). Coarse-and fine-grained attention network with background-aware loss for crowd density map estimation. In WACV.","DOI":"10.1109\/WACV48630.2021.00372"},{"key":"1990_CR59","doi-asserted-by":"crossref","unstructured":"Sam, D.B., Surya, S., & Babu, R.V. (2017). Switching convolutional neural network for crowd counting. In CVPR.","DOI":"10.1109\/CVPR.2017.429"},{"key":"1990_CR60","doi-asserted-by":"crossref","unstructured":"Shen, Z., Xu, Y., Ni, B., Wang, M., Hu, J., Yang, X. (2018a). Crowd counting via adversarial cross-scale consistency pursuit. In CVPR.","DOI":"10.1109\/CVPR.2018.00550"},{"key":"1990_CR61","doi-asserted-by":"crossref","unstructured":"Shen, Z., Xu, Y., Ni, B., Wang, M., Hu, J., & Yang, X. (2018b). Crowd counting via adversarial cross-scale consistency pursuit. In CVPR.","DOI":"10.1109\/CVPR.2018.00550"},{"key":"1990_CR62","doi-asserted-by":"crossref","unstructured":"Shi, M., Yang, Z., Xu, C., & Chen, Q. (2019a). Revisiting perspective information for efficient crowd counting. In CVPR.","DOI":"10.1109\/CVPR.2019.00745"},{"key":"1990_CR63","doi-asserted-by":"crossref","unstructured":"Shi, Z., Zhang, L., Liu, Y., Cao, X., & Ye, Y., Cheng, M.M., Zheng, G. (2018a). Crowd counting with deep negative correlation learning. In CVPR.","DOI":"10.1109\/CVPR.2018.00564"},{"issue":"11","key":"1990_CR64","first-page":"4953","volume":"14","author":"Z Shi","year":"2018","unstructured":"Shi, Z., Zhang, L., Sun, Y., & Ye, Y. (2018). Multiscale multitask deep netvlad for crowd counting. IEEE TII, 14(11), 4953\u20134962.","journal-title":"IEEE TII"},{"key":"1990_CR65","doi-asserted-by":"crossref","unstructured":"Shi, Z., Mettes, P., & Snoek, C.G.M. (2019b). Counting with focus for free. In ICCV,","DOI":"10.1109\/ICCV.2019.00430"},{"key":"1990_CR66","doi-asserted-by":"publisher","first-page":"7472","DOI":"10.1109\/TIP.2021.3106812","volume":"30","author":"Z Shi","year":"2021","unstructured":"Shi, Z., Chen, Y., Gavves, E., Mettes, P., & Snoek, C. G. (2021). Unsharp mask guided filtering. IEEE Transactions on Image Processing, 30, 7472\u20137485.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1990_CR67","doi-asserted-by":"crossref","unstructured":"Shi, Z., Mettes, P., Zheng, G., Snoek, C. (2021b). Frequency-supervised mr-to-ct image synthesis. In MICCAI workshop on deep generative models and data augmentation.","DOI":"10.1007\/978-3-030-88210-5_1"},{"key":"1990_CR68","doi-asserted-by":"crossref","unstructured":"Shi, Z., Sun, Y., Zhang, M. (2024). Training-free object counting with prompts. In WACV.","DOI":"10.1109\/WACV57701.2024.00039"},{"key":"1990_CR69","doi-asserted-by":"crossref","unstructured":"Shu, W., Wan, J., Tan, K.C., Kwong, S., Chan, A.B. (2022). Crowd counting in the frequency domain. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01900"},{"key":"1990_CR70","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Patel, V.M. (2017). Generating high-quality crowd density maps using contextual pyramid cnns. In ICCV pp. 1861\u20131870.","DOI":"10.1109\/ICCV.2017.206"},{"key":"1990_CR71","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1109\/TIP.2019.2928634","volume":"29","author":"VA Sindagi","year":"2019","unstructured":"Sindagi, V. A., & Patel, V. M. (2019). Ha-CCN: Hierarchical attention-based crowd counting network. IEEE Transactions on Image Processing, 29, 323\u2013335.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1990_CR72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3035969","author":"VA Sindagi","year":"2020","unstructured":"Sindagi, V. A., Yasarla, R., & Patel, V. M. (2020). Jhu-crowd++: Large-scale crowd counting dataset and a benchmark method. IEEE Transactions on Pattern Analysis and Machine Intelligence. https:\/\/doi.org\/10.1109\/TPAMI.2020.3035969","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1990_CR73","doi-asserted-by":"crossref","unstructured":"Song, Q., Wang, C., Jiang, Z., Wang, Y., Tai, Y., Wang, C., Li, J., Huang, F., Wu, Y. (2021). Rethinking counting and localization in crowds: A purely point-based framework. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"1990_CR74","unstructured":"Sun, G., Liu, Y., Probst, T., Paudel, D.P., Popovic, N., & Van\u00a0Gool, L. (2021). Boosting crowd counting with transformers. arXiv:2105.10926"},{"key":"1990_CR75","unstructured":"Tian, Y., Chu, X., Wang, H. (2021). Cctrans: Simplifying and improving crowd counting with transformer. arXiv:2109.14483"},{"key":"1990_CR76","doi-asserted-by":"crossref","unstructured":"Topkaya, I.S., Erdogan, H., Porikli, F. (2014). Counting people by clustering person detector outputs. In AVSS","DOI":"10.1109\/AVSS.2014.6918687"},{"key":"1990_CR77","unstructured":"Tran, N.H., Huy, T.D., Duong, S.T,, Nguyen, P., Hung, D.H., Nguyen, C.D.T., Bui, T., Truong, S.Q., & VinBrain, J. (2022). Improving local features with relevant spatial information by vision transformer for crowd counting. In BMVC."},{"key":"1990_CR78","unstructured":"Wan, J., Chan, A. (2020). Modeling noisy annotations for crowd counting. In NeurIPS"},{"issue":"3","key":"1990_CR79","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1109\/TPAMI.2020.3022878","volume":"44","author":"J Wan","year":"2020","unstructured":"Wan, J., Wang, Q., & Chan, A. B. (2020). Kernel-based density map generation for dense object counting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(3), 1357\u20131370.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1990_CR80","doi-asserted-by":"crossref","unstructured":"Wan, J., Liu, Z., Chan, A.B. (2021). A generalized loss function for crowd counting and localization. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"1990_CR81","unstructured":"Wang, B., Liu, H., Samaras, D., Hoai, M. (2020a). Distribution matching for crowd counting. In NeurIPS."},{"key":"1990_CR82","doi-asserted-by":"crossref","unstructured":"Wang, C., Song, Q., Zhang, B., Wang, Y., Tai, Y., Hu, X., Wang, C., Li, J., Ma, J., & Wu, Y. (2021). Uniformity in heterogeneity: Diving deep into count interval partition for crowd counting. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00322"},{"issue":"6","key":"1990_CR83","doi-asserted-by":"publisher","first-page":"2141","DOI":"10.1109\/TPAMI.2020.3013269","volume":"43","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Gao, J., Lin, W., & Li, X. (2020). Nwpu-crowd: A large-scale benchmark for crowd counting and localization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(6), 2141\u20132149.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1s","key":"1990_CR84","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3465455","volume":"18","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Ma, Z., Wei, X., Zheng, S., Wang, Y., & Hong, X. (2022). Eccnas: Efficient crowd counting neural architecture search. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 18(1s), 1\u201319.","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"1990_CR85","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., & Kweon, I.S. (2018). Cbam: Convolutional block attention module. In ECCV.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1990_CR86","doi-asserted-by":"crossref","unstructured":"Wu, B., & Nevatia, R. (2007). Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors. International Journal of Computer Vision, 75(2), 247.","DOI":"10.1007\/s11263-006-0027-7"},{"issue":"7","key":"1990_CR87","doi-asserted-by":"publisher","first-page":"1722","DOI":"10.1007\/s11263-023-01782-1","volume":"131","author":"H Xiong","year":"2023","unstructured":"Xiong, H., Lu, H., Liu, C., Liu, L., Shen, C., & Cao, Z. (2023). From open set to closed set: Supervised spatial divide-and-conquer for object counting. International Journal of Computer Vision., 131(7), 1722\u20131740.","journal-title":"International Journal of Computer Vision."},{"issue":"2","key":"1990_CR88","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. (2022). Autoscale: Learning to scale for crowd counting. International Journal of Computer Vision, 130(2), 405\u2013434.","journal-title":"International Journal of Computer Vision"},{"key":"1990_CR89","doi-asserted-by":"crossref","unstructured":"Yan, Z., Yuan, Y., Zuo, W., Tan, X., Wang, Y., Wen, S., & Ding, E. (2019). Perspective-guided convolution networks for crowd counting. In ICCV.","DOI":"10.1109\/ICCV.2019.00104"},{"key":"1990_CR90","doi-asserted-by":"crossref","unstructured":"Yang, S., Guo, W., Ren, Y. (2022). Crowdformer: An overlap patching vision transformer for top-down crowd counting. In IJCAI.","DOI":"10.24963\/ijcai.2022\/215"},{"key":"1990_CR91","doi-asserted-by":"crossref","unstructured":"Yang, Y., Li, G., Wu, Z., Su, L., Huang, Q., Sebe, N. (2020). Reverse perspective network for perspective-aware object counting. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00443"},{"key":"1990_CR92","doi-asserted-by":"crossref","unstructured":"Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z.H., Tay, F.E., Feng, J., & Yan, S. (2021). Tokens-to-token vit: Training vision transformers from scratch on imagenet. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"1990_CR93","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., & Yoo, Y. (2019). Cutmix: Regularization strategy to train strong classifiers with localizable features. In ICCV.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"1990_CR94","doi-asserted-by":"crossref","unstructured":"Zhang, J., Cheng, Z.Q., Wu, X., Li, W., Qiao, J.J. (2022). Crossnet: Boosting crowd counting with localization. In ACM MM.","DOI":"10.1145\/3503161.3547863"},{"issue":"8","key":"1990_CR95","doi-asserted-by":"publisher","first-page":"1938","DOI":"10.1007\/s11263-022-01626-4","volume":"130","author":"Q Zhang","year":"2022","unstructured":"Zhang, Q., & Chan, A. B. (2022). Wide-area crowd counting: Multi-view fusion networks for counting in large scenes. International Journal of Computer Vision, 130(8), 1938\u20131960.","journal-title":"International Journal of Computer Vision"},{"key":"1990_CR96","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 CVPR.","DOI":"10.1109\/CVPR.2016.70"},{"key":"1990_CR97","doi-asserted-by":"crossref","unstructured":"Zhao, M., Zhang, J., Zhang, C., & Zhang, W. (2019). Leveraging heterogeneous auxiliary tasks to assist crowd counting. In CVPR.","DOI":"10.1109\/CVPR.2019.01302"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-01990-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-01990-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-01990-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,19]],"date-time":"2024-06-19T13:16:41Z","timestamp":1718803001000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-01990-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,9]]},"references-count":97,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["1990"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-01990-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,9]]},"assertion":[{"value":"8 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}