{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T19:10:20Z","timestamp":1783797020287,"version":"3.55.0"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012274","type":"print"},{"value":"9783030012281","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-01228-1_45","type":"book-chapter","created":{"date-parts":[[2018,10,6]],"date-time":"2018-10-06T01:03:51Z","timestamp":1538787831000},"page":"757-773","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":526,"title":["Scale Aggregation Network for Accurate and Efficient Crowd Counting"],"prefix":"10.1007","author":[{"given":"Xinkun","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhipeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanyun","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,10,6]]},"reference":[{"issue":"5\u20136","key":"45_CR1","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s00138-008-0132-4","volume":"19","author":"B Zhan","year":"2008","unstructured":"Zhan, B., Monekosso, D.N., Remagnino, P., Velastin, S.A., Xu, L.Q.: Crowd analysis: a survey. Mach. Vis. Appl. 19(5\u20136), 345\u2013357 (2008)","journal-title":"Mach. Vis. Appl."},{"issue":"3","key":"45_CR2","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1109\/TCSVT.2014.2358029","volume":"25","author":"T Li","year":"2015","unstructured":"Li, T., Chang, H., Wang, M., Ni, B., Hong, R., Yan, S.: Crowded scene analysis: a survey. IEEE Trans. Circuits Syst. Video Technol. 25(3), 367\u2013386 (2015)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"45_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-image crowd counting via multi-column convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 589\u2013597 (2016)","DOI":"10.1109\/CVPR.2016.70"},{"key":"45_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1007\/978-3-319-46478-7_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"D O\u00f1oro-Rubio","year":"2016","unstructured":"O\u00f1oro-Rubio, D., L\u00f3pez-Sastre, R.J.: Towards perspective-free object counting with deep learning. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9911, pp. 615\u2013629. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46478-7_38"},{"key":"45_CR5","doi-asserted-by":"crossref","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, vol. 1, p. 6 (2017)","DOI":"10.1109\/CVPR.2017.429"},{"key":"45_CR6","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Patel, V.M.: Generating high-quality crowd density maps using contextual pyramid CNNS. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 1879\u20131888. IEEE (2017)","DOI":"10.1109\/ICCV.2017.206"},{"key":"45_CR7","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1125\u20131134 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"45_CR8","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672\u20132680 (2014)"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Szegedy, C., et al.: Going deeper with convolutions. IEEE (2015)","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"45_CR10","unstructured":"Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for neural networks for image processing. IEEE Trans. Comput. Imaging (2017)"},{"issue":"4","key":"45_CR11","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. CoRR, abs\/1703.06868 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Ge, W., Collins, R.T.: Marked point processes for crowd counting. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009, pp. 2913\u20132920. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206621"},{"key":"45_CR14","doi-asserted-by":"crossref","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, ICPR 2008, pp. 1\u20134. IEEE (2008)","DOI":"10.1109\/ICPR.2008.4761705"},{"issue":"4","key":"45_CR15","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1109\/TPAMI.2011.155","volume":"34","author":"P Dollar","year":"2012","unstructured":"Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 743\u2013761 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"45_CR16","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627\u20131645 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Leibe, B., Seemann, E., Schiele, B.: Pedestrian detection in crowded scenes. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005. vol. 1, pp. 878\u2013885. IEEE (2005)","DOI":"10.1109\/CVPR.2005.272"},{"key":"45_CR18","doi-asserted-by":"crossref","unstructured":"Chan, A.B., Vasconcelos, N.: Bayesian poisson regression for crowd counting. In: IEEE 12th International Conference on Computer Vision, pp. 545\u2013551. IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459191"},{"key":"45_CR19","doi-asserted-by":"crossref","unstructured":"Chen, K., Loy, C.C., Gong, S., Xiang, T.: Feature mining for localised crowd counting. In: BMVC, vol. 1, p. 3 (2012)","DOI":"10.5244\/C.26.21"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Ryan, D., Denman, S., Fookes, C., Sridharan, S.: Crowd counting using multiple local features. In: Digital Image Computing: Techniques and Applications, DICTA 2009, pp. 81\u201388. IEEE (2009)","DOI":"10.1109\/DICTA.2009.22"},{"key":"45_CR21","doi-asserted-by":"crossref","unstructured":"Idrees, H., Saleemi, I., Seibert, C., Shah, M.: Multi-source multi-scale counting in extremely dense crowd images. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2547\u20132554. IEEE (2013)","DOI":"10.1109\/CVPR.2013.329"},{"issue":"13","key":"45_CR22","doi-asserted-by":"publisher","first-page":"3812","DOI":"10.1093\/nar\/gkg509","volume":"31","author":"PC Ng","year":"2003","unstructured":"Ng, P.C., Henikoff, S.: Sift: predicting amino acid changes that affect protein function. Nucleic Acids Res. 31(13), 3812\u20133814 (2003)","journal-title":"Nucleic Acids Res."},{"key":"45_CR23","unstructured":"Lempitsky, V., Zisserman, A.: Learning to count objects in images. In: Advances in Neural Information Processing Systems, pp. 1324\u20131332 (2010)"},{"key":"45_CR24","doi-asserted-by":"crossref","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\u20133261 (2015)","DOI":"10.1109\/ICCV.2015.372"},{"key":"45_CR25","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.patrec.2017.07.007","volume":"107","author":"VA Sindagi","year":"2017","unstructured":"Sindagi, V.A., Patel, V.M.: A survey of recent advances in cnn-based single image crowd counting and density estimation. Pattern Recognit. Lett. 107, 3\u201316 (2017)","journal-title":"Pattern Recognit. Lett."},{"key":"45_CR26","doi-asserted-by":"crossref","unstructured":"Wang, C., Zhang, H., Yang, L., Liu, S., Cao, X.: Deep people counting in extremely dense crowds. In: Proceedings of the 23rd ACM International Conference on Multimedia, pp. 1299\u20131302. ACM (2015)","DOI":"10.1145\/2733373.2806337"},{"key":"45_CR27","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"45_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, C., Li, H., Wang, X., Yang, X.: Cross-scene crowd counting via deep convolutional neural networks. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 833\u2013841. IEEE (2015)","DOI":"10.1109\/CVPR.2016.70"},{"key":"45_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1007\/978-3-319-46475-6_41","volume-title":"Computer Vision \u2013 ECCV 2016","author":"E Walach","year":"2016","unstructured":"Walach, E., Wolf, L.: Learning to count with CNN boosting. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 660\u2013676. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_41"},{"key":"45_CR30","doi-asserted-by":"crossref","unstructured":"Shang, C., Ai, H., Bai, B.: End-to-end crowd counting via joint learning local and global count. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 1215\u20131219. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7532551"},{"key":"45_CR31","doi-asserted-by":"crossref","unstructured":"Boominathan, L., Kruthiventi, S.S., Babu, R.V.: Crowdnet: a deep convolutional network for dense crowd counting. In: Proceedings of the 2016 ACM on Multimedia Conference, pp. 640\u2013644. ACM (2016)","DOI":"10.1145\/2964284.2967300"},{"key":"45_CR32","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Patel, V.M.: CNN-based cascaded multi-task learning of high-level prior and density estimation for crowd counting. In: 2017 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 1\u20136. IEEE (2017)","DOI":"10.1109\/AVSS.2017.8078491"},{"key":"45_CR33","doi-asserted-by":"crossref","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 (2018)","DOI":"10.1109\/CVPR.2018.00120"},{"key":"45_CR34","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"45_CR35","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456 (2015)"},{"key":"45_CR36","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"45_CR37","unstructured":"Paszke, A., et al.: Pytorch: tensors and dynamic neural networks in python with strong GPU acceleration, May 2017"},{"key":"45_CR38","doi-asserted-by":"crossref","unstructured":"Chan, A.B., Liang, Z.S.J., Vasconcelos, N.: Privacy preserving crowd monitoring: counting people without people models or tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2008, pp. 1\u20137. IEEE (2008)","DOI":"10.1109\/CVPR.2008.4587569"},{"issue":"3","key":"45_CR39","doi-asserted-by":"publisher","first-page":"1049","DOI":"10.1109\/TIP.2017.2740160","volume":"27","author":"S Huang","year":"2018","unstructured":"Huang, S., et al.: Body structure aware deep crowd counting. IEEE Trans. Image Process. 27(3), 1049\u20131059 (2018)","journal-title":"IEEE Trans. Image Process."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01228-1_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T18:43:34Z","timestamp":1775241814000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01228-1_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012274","9783030012281"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01228-1_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"6 October 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}