{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,26]],"date-time":"2026-07-26T05:30:42Z","timestamp":1785043842847,"version":"3.55.0"},"reference-count":82,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T00:00:00Z","timestamp":1653868800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T00:00:00Z","timestamp":1653868800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Research Grants Council of the Hong Kong SAR, China","award":["No. T32-101\/15-R, CityU 11212518"],"award-info":[{"award-number":["No. T32-101\/15-R, CityU 11212518"]}]},{"DOI":"10.13039\/100007567","name":"City University of Hong Kong","doi-asserted-by":"publisher","award":["7004887"],"award-info":[{"award-number":["7004887"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s11263-022-01626-4","type":"journal-article","created":{"date-parts":[[2022,5,30]],"date-time":"2022-05-30T03:23:26Z","timestamp":1653881006000},"page":"1938-1960","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Wide-Area Crowd Counting: Multi-view Fusion Networks for Counting in Large Scenes"],"prefix":"10.1007","volume":"130","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6212-9799","authenticated-orcid":false,"given":"Qi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antoni B.","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,5,30]]},"reference":[{"issue":"10","key":"1626_CR1","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/2001269.2001293","volume":"54","author":"S Agarwal","year":"2011","unstructured":"Agarwal, S., Furukawa, Y., Snavely, N., Simon, I., Curless, B., Seitz, S. M., & Szeliski, R. (2011). Building rome in a day. Communications of the ACM, 54(10), 105\u2013112.","journal-title":"Communications of the ACM"},{"key":"1626_CR2","doi-asserted-by":"crossref","unstructured":"Ammar, Abbas S., & Zisserman, A.,(2019) A geometric approach to obtain a bird\u2019s eye view from an image. In Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops.","DOI":"10.1109\/ICCVW.2019.00504"},{"issue":"3\u20134","key":"1626_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3199667","volume":"14","author":"R Bhardwaj","year":"2018","unstructured":"Bhardwaj, R., Tummala, G. K., Ramalingam, G., Ramjee, R., & Sinha, P. (2018). Autocalib: Automatic traffic camera calibration at scale. ACM Transactions on Sensor Networks (TOSN), 14(3\u20134), 1\u201327.","journal-title":"ACM Transactions on Sensor Networks (TOSN)"},{"key":"1626_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 Proceedings of the European Conference on Computer Vision (ECCV), pp 734\u2013750.","DOI":"10.1007\/978-3-030-01228-1_45"},{"issue":"4","key":"1626_CR5","doi-asserted-by":"publisher","first-page":"2160","DOI":"10.1109\/TIP.2011.2172800","volume":"21","author":"AB Chan","year":"2012","unstructured":"Chan, A. B., & Vasconcelos, N. (2012). 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":"1626_CR6","doi-asserted-by":"crossref","unstructured":"Chan AB, Liang ZSJ, Vasconcelos, N. (2008) Privacy preserving crowd monitoring: Counting people without people models or tracking. In Computer Vision and Pattern Recognition, pp 1\u20137","DOI":"10.1109\/CVPR.2008.4587569"},{"key":"1626_CR7","doi-asserted-by":"crossref","unstructured":"Chen, C., Li, G., Xu, R., Chen, T., Wang, M., & Lin, L. (2019) Clusternet: Deep hierarchical cluster network with rigorously rotation-invariant representation for point cloud analysis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4994\u20135002.","DOI":"10.1109\/CVPR.2019.00513"},{"key":"1626_CR8","volume-title":"Crowd Counting and Profiling: Methodology and Evaluation","author":"CL Chen","year":"2013","unstructured":"Chen, C. L., Chen, K., Gong, S., & Xiang, T. (2013). Crowd Counting and Profiling: Methodology and Evaluation. New York: Springer."},{"key":"1626_CR9","doi-asserted-by":"crossref","unstructured":"Chen, K., Chen, LC., Gong, S., & Xiang, T. (2012) Feature mining for localised crowd counting. In: BMVC","DOI":"10.5244\/C.26.21"},{"key":"1626_CR10","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.neucom.2014.01.019","volume":"136","author":"Zhongwei Cheng","year":"2014","unstructured":"Cheng, Zhongwei, Qin, Lei, Huang, Qingming, Yan, Shuicheng, & Tian, Qi. (2014). Recognizing human group action by layered model with multiple cues. Neurocomputing, 136, 124\u2013135. https:\/\/doi.org\/10.1016\/j.neucom.2014.01.019","journal-title":"Neurocomputing"},{"key":"1626_CR11","unstructured":"Cohen, T., & Welling, M. (2016) Group equivariant convolutional networks. In International conference on machine learning, pp 2990\u20132999."},{"key":"1626_CR12","unstructured":"Dieleman, S., De Fauw, J., & Kavukcuoglu, K. (2016) Exploiting cyclic symmetry in convolutional neural networks. arXiv preprint arXiv:1602.02660"},{"key":"1626_CR13","unstructured":"Dittrich, F., de Oliveira, LE., Britto, Jr AS., & Koerich, AL. (2017) People counting in crowded and outdoor scenes using a hybrid multi-camera approach. arXiv preprint arXiv:1704.00326"},{"key":"1626_CR14","doi-asserted-by":"crossref","unstructured":"Eiselein, V., Fradi, H., Keller, I., Sikora, T., & Dugelay, JL. (2013) Enhancing human detection using crowd density measures and an adaptive correction filter. In 10th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), IEEE, pp 19\u201324.","DOI":"10.1109\/AVSS.2013.6636610"},{"key":"1626_CR15","doi-asserted-by":"crossref","unstructured":"Ferryman, J., & Shahrokni, A. (2009) Pets2009: Dataset and challenge. In 2009 Twelfth IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, IEEE, pp 1\u20136.","DOI":"10.1109\/PETS-WINTER.2009.5399556"},{"issue":"11","key":"1626_CR16","doi-asserted-by":"publisher","first-page":"2188","DOI":"10.1109\/TPAMI.2011.70","volume":"33","author":"J. Gall","year":"2011","unstructured":"Gall, J. ., Yao, A. ., Razavi, N. ., Van Gool, L. ., & Lempitsky, V. . (2011). Hough forests for object detection, tracking, and action recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(11), 2188\u20132202. https:\/\/doi.org\/10.1109\/TPAMI.2011.70","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1626_CR17","doi-asserted-by":"crossref","unstructured":"Gao, H., & Ji, S. (2017) Efficient and invariant convolutional neural networks for dense prediction. In 2017 IEEE International Conference on Data Mining (ICDM), IEEE, pp 871\u2013876.","DOI":"10.1109\/ICDM.2017.107"},{"key":"1626_CR18","doi-asserted-by":"crossref","unstructured":"Ge, W., & Collins, RT. (2010) Crowd detection with a multiview sampler. In European Conference on Computer Vision, pp 324\u2013337.","DOI":"10.1007\/978-3-642-15555-0_24"},{"key":"1626_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 Iberian Conference on Pattern Recognition and Image Analysis, Springer, pp 423\u2013431.","DOI":"10.1007\/978-3-319-19390-8_48"},{"key":"1626_CR20","doi-asserted-by":"crossref","unstructured":"Idrees, H., Tayyab, M., Athrey, K., Zhang, D., Al-Maadeed, S., Rajpoot, N., & Shah, M. (2018) Composition loss for counting, density map estimation and localization in dense crowds. In Proceedings of the European Conference on Computer Vision (ECCV).","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"1626_CR21","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., & Kavukcuoglu, K. (2015) Spatial transformer networks. In Advances in Neural Information Processing Systems (NIPS), pp 2017\u20132025."},{"key":"1626_CR22","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, pp 6133\u20136142.","DOI":"10.1109\/CVPR.2019.00629"},{"key":"1626_CR23","doi-asserted-by":"crossref","unstructured":"Joachims, T. (1998) Text categorization with support vector machines: Learning with many relevant features. In European conference on machine learning, Springer, pp 137\u2013142.","DOI":"10.1007\/BFb0026683"},{"issue":"5","key":"1626_CR24","first-page":"66","volume":"27","author":"JCSJ Junior","year":"2010","unstructured":"Junior, J. C. S. J., Musse, S. R., & Jung, C. R. (2010). Crowd analysis using computer vision techniques. IEEE Signal Processing Magazine, 27(5), 66\u201377.","journal-title":"IEEE Signal Processing Magazine"},{"key":"1626_CR25","unstructured":"Kang, D., & Chan, A. (2018) Crowd counting by adaptively fusing predictions from an image pyramid. In BMVC."},{"key":"1626_CR26","unstructured":"Kang, D., Dhar, D., & Chan, A. (2017) Incorporating side information by adaptive convolution. In Advances in Neural Information Processing Systems, pp 3867\u20133877."},{"key":"1626_CR27","doi-asserted-by":"crossref","unstructured":"Kang, D., Ma, Z., & Chan AB (2018) Beyond counting: Comparisons of density maps for crowd analysis tasks-counting, detection, and tracking. IEEE Transactions on Circuits and Systems for Video Technology.","DOI":"10.1109\/TCSVT.2018.2837153"},{"key":"1626_CR28","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, GE. (2012) Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pp 1097\u20131105."},{"key":"1626_CR29","doi-asserted-by":"crossref","unstructured":"Laptev, D., Savinov, N., Buhmann, JM., Pollefeys, M. (2016) Ti-pooling: Transformation-invariant pooling for feature learning in convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 289\u2013297.","DOI":"10.1109\/CVPR.2016.38"},{"key":"1626_CR30","unstructured":"Leal-Taix\u00e9, L., Milan, A., Reid, I., Roth, S., Schindler, K. (2015) Motchallenge 2015: Towards a benchmark for multi-target tracking. arXiv preprint arXiv:1504.01942"},{"key":"1626_CR31","unstructured":"Lempitsky, V., & Zisserman, A. (2010) Learning to count objects in images. In Advances in Neural Information Processing Systems, pp 1324\u20131332."},{"key":"1626_CR32","doi-asserted-by":"crossref","unstructured":"Li J, Huang, L., & Liu, C. (2012) People counting across multiple cameras for intelligent video surveillance. In IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance (AVSS), IEEE, pp 178\u2013183.","DOI":"10.1109\/AVSS.2012.54"},{"key":"1626_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 Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1091\u20131100.","DOI":"10.1109\/CVPR.2018.00120"},{"key":"1626_CR34","doi-asserted-by":"crossref","unstructured":"Lian, D., Li, J., Zheng, J., Luo, W., & Gao, S. (2019) Density map regression guided detection network for rgb-d crowd counting and localization. In CVPR, pp 1821\u20131830.","DOI":"10.1109\/CVPR.2019.00192"},{"key":"1626_CR35","doi-asserted-by":"crossref","unstructured":"Liu, C., Weng, X., & Mu, Y. (2019a) Recurrent attentive zooming for joint crowd counting and precise localization. In CVPR, pp 1217\u20131226.","DOI":"10.1109\/CVPR.2019.00131"},{"key":"1626_CR36","doi-asserted-by":"crossref","unstructured":"Liu, J., Gao, C., Meng, D., & Hauptmann, AG. (2018) Decidenet: Counting varying density crowds through attention guided detection and density estimation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5197\u20135206.","DOI":"10.1109\/CVPR.2018.00545"},{"key":"1626_CR37","doi-asserted-by":"crossref","unstructured":"Liu, L., Qiu, Z., Li, G., Liu, S., Ouyang, W., & Lin, L. (2019b) Crowd counting with deep structured scale integration network. In The IEEE International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV.2019.00186"},{"key":"1626_CR38","doi-asserted-by":"crossref","unstructured":"Liu, W., Salzmann, M., & Fua, P. (2019c) Context-aware crowd counting. In CVPR, pp 5099\u20135108.","DOI":"10.1109\/CVPR.2019.00524"},{"key":"1626_CR39","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 Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXIV 16, Springer, pp 241\u2013257.","DOI":"10.1007\/978-3-030-58586-0_15"},{"issue":"2","key":"1626_CR40","first-page":"31","volume":"3","author":"H Ma","year":"2012","unstructured":"Ma, H., Zeng, C., & Ling, C. X. (2012). A reliable people counting system via multiple cameras. ACM Transactions on Intelligent Systems and Technology (TIST), 3(2), 31.","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"1626_CR41","doi-asserted-by":"crossref","unstructured":"Ma, Z., Yu, L., & Chan, AB. (2015) Small instance detection by integer programming on object density maps. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 3689\u20133697.","DOI":"10.1109\/CVPR.2015.7298992"},{"key":"1626_CR42","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.patrec.2013.10.006","volume":"36","author":"L Maddalena","year":"2014","unstructured":"Maddalena, L., Petrosino, A., & Russo, F. (2014). People counting by learning their appearance in a multi-view camera environment. Pattern Recognition Letters, 36, 125\u2013134.","journal-title":"Pattern Recognition Letters"},{"key":"1626_CR43","doi-asserted-by":"crossref","unstructured":"Marana, A., Costa, LdF., Lotufo, R., & Velastin, S. (1998) On the efficacy of texture analysis for crowd monitoring. In International Symposium on Computer Graphics, Image Processing, and Vision, IEEE, pp 354\u2013361.","DOI":"10.1109\/SIBGRA.1998.722773"},{"key":"1626_CR44","doi-asserted-by":"crossref","unstructured":"Marcos, D., Volpi, M., Komodakis, N., & Tuia, D. (2017) Rotation equivariant vector field networks. In Proceedings of the IEEE International Conference on Computer Vision, pp 5048\u20135057.","DOI":"10.1109\/ICCV.2017.540"},{"key":"1626_CR45","doi-asserted-by":"crossref","unstructured":"Onoro-Rubio, D., & L\u00f3pez-Sastre, RJ. (2016) Towards perspective-free object counting with deep learning. In European Conference on Computer Vision, Springer, pp 615\u2013629.","DOI":"10.1007\/978-3-319-46478-7_38"},{"key":"1626_CR46","doi-asserted-by":"crossref","unstructured":"Paragios, N., & Ramesh, V. (2001) A mrf-based approach for real-time subway monitoring. In Computer Vision and Pattern Recognition, IEEE, vol\u00a01.","DOI":"10.1109\/CVPR.2001.990644"},{"key":"1626_CR47","doi-asserted-by":"crossref","unstructured":"Pham, VQ., Kozakaya, T., Yamaguchi, O., & Okada, R. (2015) Count forest: Co-voting uncertain number of targets using random forest for crowd density estimation. In Proceedings of the IEEE International Conference on Computer Vision, pp 3253\u20133261.","DOI":"10.1109\/ICCV.2015.372"},{"key":"1626_CR48","doi-asserted-by":"crossref","unstructured":"Ranjan, V., Le, H., & Hoai, M. (2018) Iterative crowd counting. In ECCV, pp 270\u2013285.","DOI":"10.1007\/978-3-030-01234-2_17"},{"key":"1626_CR49","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, pp 91\u201399."},{"key":"1626_CR50","doi-asserted-by":"crossref","unstructured":"Ren, W., Kang, D., Tang, Y., & Chan, AB. (2018) Fusing crowd density maps and visual object trackers for people tracking in crowd scenes. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 5353\u20135362.","DOI":"10.1109\/CVPR.2018.00561"},{"key":"1626_CR51","doi-asserted-by":"crossref","unstructured":"Ristani, E., Solera, F., Zou, R., Cucchiara, R., & Tomasi, C. (2016) Performance measures and a data set for multi-target, multi-camera tracking. In European Conference on Computer Vision workshop on Benchmarking Multi-Target Tracking.","DOI":"10.1007\/978-3-319-48881-3_2"},{"key":"1626_CR52","doi-asserted-by":"crossref","unstructured":"Rodriguez, M., Laptev, I., Sivic, J., & Audibert, JY. (2011) Density-aware person detection and tracking in crowds. In IEEE International Conference on Computer Vision (ICCV), IEEE, pp 2423\u20132430.","DOI":"10.1109\/ICCV.2011.6126526"},{"issue":"8","key":"1626_CR53","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.patrec.2013.10.002","volume":"44","author":"D Ryan","year":"2014","unstructured":"Ryan, D., Denman, S., Fookes, C., & Sridharan, S. (2014). Scene invariant multi camera crowd counting. Pattern Recognition Letters, 44(8), 98\u2013112.","journal-title":"Pattern Recognition Letters"},{"key":"1626_CR54","doi-asserted-by":"crossref","unstructured":"Sabzmeydani, P., & Mori, G. (2007) Detecting pedestrians by learning shapelet features. In IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp 1\u20138.","DOI":"10.1109\/CVPR.2007.383134"},{"key":"1626_CR55","doi-asserted-by":"crossref","unstructured":"Sam, DB., Surya, S., & Babu, RV. (2017) Switching convolutional neural network for crowd counting. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, vol\u00a01, p\u00a06.","DOI":"10.1109\/CVPR.2017.429"},{"key":"1626_CR56","doi-asserted-by":"crossref","unstructured":"Shen, Z., Xu, Y., Ni, B., Wang, M., Hu, J., & Yang, X. (2018) Crowd counting via adversarial cross-scale consistency pursuit. In Computer Vision and Pattern Recognition, pp 5245\u20135254.","DOI":"10.1109\/CVPR.2018.00550"},{"key":"1626_CR57","doi-asserted-by":"crossref","unstructured":"Shi, M., Yang, Z., Xu, C., & Chen, Q. (2019) Revisiting perspective information for efficient crowd counting. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7279\u20137288.","DOI":"10.1109\/CVPR.2019.00745"},{"key":"1626_CR58","doi-asserted-by":"crossref","unstructured":"Shi, Z., Zhang, L., Liu, Y., Cao, X., Ye, Y., Cheng, MM., & Zheng, G. (2018) Crowd counting with deep negative correlation learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5382\u20135390.","DOI":"10.1109\/CVPR.2018.00564"},{"key":"1626_CR59","doi-asserted-by":"crossref","unstructured":"Sindagi, VA., & Patel, VM. (2017) Generating high-quality crowd density maps using contextual pyramid cnns. In IEEE International Conference on Computer Vision (ICCV), IEEE, pp 1879\u20131888.","DOI":"10.1109\/ICCV.2017.206"},{"key":"1626_CR60","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.patrec.2017.07.007","volume":"107","author":"VA Sindagi","year":"2018","unstructured":"Sindagi, V. A., & Patel, V. M. (2018). A survey of recent advances in cnn-based single image crowd counting and density estimation. Pattern Recognition Letters, 107, 3\u201316.","journal-title":"Pattern Recognition Letters"},{"key":"1626_CR61","doi-asserted-by":"crossref","unstructured":"Snavely, N., Seitz, SM., & Szeliski, R. (2006) Photo tourism: Exploring photo collections in 3d. In ACM siggraph 2006 papers, pp 835\u2013846.","DOI":"10.1145\/1141911.1141964"},{"key":"1626_CR62","doi-asserted-by":"crossref","unstructured":"Sun, Y., Cheng, C., Zhang, Y., Zhang, C., Zheng, L., Wang, Z., & Wei, Y. (2020) Circle loss: A unified perspective of pair similarity optimization. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6398\u20136407.","DOI":"10.1109\/CVPR42600.2020.00643"},{"issue":"1","key":"1626_CR63","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1109\/TIP.2014.2363445","volume":"24","author":"N Tang","year":"2014","unstructured":"Tang, N., Lin, Y. Y., Weng, M. F., & Liao, H. Y. (2014). Cross-camera knowledge transfer for multiview people counting. IEEE Transactions on Image Processing, 24(1), 80\u201393.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"2","key":"1626_CR64","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. (2004). Robust real-time face detection. International Journal of Computer Vision, 57(2), 137\u2013154.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"1626_CR65","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/s11263-005-6644-8","volume":"63","author":"P Viola","year":"2005","unstructured":"Viola, P., Jones, M. J., & Snow, D. (2005). Detecting pedestrians using patterns of motion and appearance. International Journal of Computer Vision, 63(2), 153\u2013161.","journal-title":"International Journal of Computer Vision"},{"key":"1626_CR66","doi-asserted-by":"crossref","unstructured":"Wang, G., Yuan, Y., Chen, X., Li, J., & Zhou, X. (2018) Learning discriminative features with multiple granularities for person re-identification. In Proceedings of the 26th ACM international conference on Multimedia, pp 274\u2013282.","DOI":"10.1145\/3240508.3240552"},{"key":"1626_CR67","doi-asserted-by":"crossref","unstructured":"Wang, Q., Gao, J., et\u00a0al .(2019) Learning from synthetic data for crowd counting in the wild. In CVPR, pp 8198\u20138207.","DOI":"10.1109\/CVPR.2019.00839"},{"key":"1626_CR68","doi-asserted-by":"crossref","unstructured":"Wang, Y., & Zou, Y. (2016) Fast visual object counting via example-based density estimation. In IEEE International Conference on Image Processing (ICIP), IEEE, pp 3653\u20133657.","DOI":"10.1109\/ICIP.2016.7533041"},{"key":"1626_CR69","doi-asserted-by":"crossref","unstructured":"Weiler, M., Hamprecht, FA., & Storath, M. (2018) Learning steerable filters for rotation equivariant cnns. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 849\u2013858.","DOI":"10.1109\/CVPR.2018.00095"},{"key":"1626_CR70","doi-asserted-by":"crossref","unstructured":"Worrall, D., & Brostow, G. (2018) Cubenet: Equivariance to 3d rotation and translation. In Proceedings of the European Conference on Computer Vision (ECCV), pp 567\u2013584.","DOI":"10.1007\/978-3-030-01228-1_35"},{"issue":"2","key":"1626_CR71","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. (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\u2013266.","journal-title":"International Journal of Computer Vision"},{"key":"1626_CR72","doi-asserted-by":"crossref","unstructured":"Xu, B., & Qiu, G. (2016) Crowd density estimation based on rich features and random projection forest. In IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, pp 1\u20138.","DOI":"10.1109\/WACV.2016.7477682"},{"key":"1626_CR73","doi-asserted-by":"crossref","unstructured":"Xu, C., Qiu, K., Fu, J., Bai, S., Xu, Y., & Bai, X. (2019) Learn to scale: Generating multipolar normalized density maps for crowd counting. In The IEEE International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV.2019.00847"},{"key":"1626_CR74","doi-asserted-by":"crossref","unstructured":"Yan, Z., Yuan, Y., Zuo, W., Tan, X., Wang, Y., Wen, S., & Ding, E. (2019a) Perspective-guided convolution networks for crowd counting. In The IEEE International Conference on Computer Vision (ICCV).","DOI":"10.1109\/ICCV.2019.00104"},{"key":"1626_CR75","doi-asserted-by":"crossref","unstructured":"Yan, Z., Yuan, Y., Zuo, W., Tan, X., Wang, Y., Wen, S., & Ding, E. (2019b) Perspective-guided convolution networks for crowd counting. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 952\u2013961.","DOI":"10.1109\/ICCV.2019.00104"},{"key":"1626_CR76","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 Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4374\u20134383.","DOI":"10.1109\/CVPR42600.2020.00443"},{"key":"1626_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, C., Li, H., Wang, X., & Yang, X. (2015) Cross-scene crowd counting via deep convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 833\u2013841.","DOI":"10.1109\/CVPR.2015.7298684"},{"key":"1626_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, Q., & Chan, AB. (2019) Wide-area crowd counting via ground-plane density maps and multi-view fusion cnns. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 8297\u20138306.","DOI":"10.1109\/CVPR.2019.00849"},{"key":"1626_CR79","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Lin, W., & Chan, AB. (2021) Cross-view cross-scene multi-view crowd counting. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 557\u2013567.","DOI":"10.1109\/CVPR46437.2021.00062"},{"key":"1626_CR80","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S,, Gaom S,, & Ma, Y. (2016) Single-image crowd counting via multi-column convolutional neural network. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp 589\u2013597.","DOI":"10.1109\/CVPR.2016.70"},{"key":"1626_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, Z. (2000) A flexible new technique for camera calibration. IEEE Transactions on Pattern Analysis and Machine Intelligence 22.","DOI":"10.1109\/34.888718"},{"key":"1626_CR82","doi-asserted-by":"crossref","unstructured":"Zheng, L., Li, Y., Mu, Y. (2021) Learning factorized cross-view fusion for multi-view crowd counting. In 2021 IEEE International Conference on Multimedia and Expo (ICME), IEEE, pp 1\u20136.","DOI":"10.1109\/ICME51207.2021.9428284"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01626-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01626-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01626-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,26]],"date-time":"2024-09-26T02:04:06Z","timestamp":1727316246000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01626-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,30]]},"references-count":82,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["1626"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01626-4","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,30]]},"assertion":[{"value":"28 December 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}