{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:50:27Z","timestamp":1784904627589,"version":"3.55.0"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732348","type":"print"},{"value":"9783031732355","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73235-5_2","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"19-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Mahalanobis Distance-Based Multi-view Optimal Transport for\u00a0Multi-view Crowd Localization"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6212-9799","authenticated-orcid":false,"given":"Qi","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7946-2455","authenticated-orcid":false,"given":"Kaiyi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2886-2513","authenticated-orcid":false,"given":"Antoni B.","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3212-0544","authenticated-orcid":false,"given":"Hui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","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, vol.\u00a035, pp. 872\u2013881 (2021)","DOI":"10.1609\/aaai.v35i2.16170"},{"key":"2_CR2","doi-asserted-by":"crossref","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4594\u20134603 (2020)","DOI":"10.1109\/CVPR42600.2020.00465"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Baqu\u00e9, P., Fleuret, F., Fua, P.: Deep occlusion reasoning for multi-camera multi-target detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 271\u2013279 (2017)","DOI":"10.1109\/ICCV.2017.38"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Chavdarova, T., et al.: Wildtrack: a multi-camera HD dataset for dense unscripted pedestrian detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5030\u20135039 (2018)","DOI":"10.1109\/CVPR.2018.00528"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Chavdarova, T., Fleuret, F.: Deep multi-camera people detection. In: 2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 848\u2013853. IEEE (2017)","DOI":"10.1109\/ICMLA.2017.00-50"},{"key":"2_CR6","doi-asserted-by":"crossref","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19638\u201319648 (2022)","DOI":"10.1109\/CVPR52688.2022.01902"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, Z.Q., Li, J.X., Dai, Q., Wu, X., Hauptmann, A.G.: Learning spatial awareness to improve crowd counting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6152\u20136161 (2019)","DOI":"10.1109\/ICCV.2019.00625"},{"issue":"2","key":"2_CR8","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1109\/TPAMI.2007.1174","volume":"30","author":"F Fleuret","year":"2007","unstructured":"Fleuret, F., Berclaz, J., Lengagne, R., Fua, P.: Multicamera people tracking with a probabilistic occupancy map. IEEE Trans. Pattern Anal. Mach. Intell. 30(2), 267\u2013282 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Ge, W., Collins, R.T.: Crowd detection with a multiview sampler. In: ECCV, pp. 324\u2013337 (2010)","DOI":"10.1007\/978-3-642-15555-0_24"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Hou, Y., Zheng, L.: Multiview detection with shadow transformer (and view-coherent data augmentation). In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1673\u20131682 (2021)","DOI":"10.1145\/3474085.3475310"},{"key":"2_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58571-6_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Hou","year":"2020","unstructured":"Hou, Y., Zheng, L., Gould, S.: Multiview detection with feature perspective transformation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 1\u201318. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_1"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Iskakov, K., Burkov, E., Lempitsky, V., Malkov, Y.: Learnable triangulation of human pose. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00781"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, X., et al.: Attention scaling for crowd counting. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"2_CR14","unstructured":"Kang, D., Chan, A.: Crowd counting by adaptively fusing predictions from an image pyramid. In: BMVC (2018)"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Laradji, I.H., Rostamzadeh, N., Pinheiro, P.O., Vazquez, D., Schmidt, M.: Where are the blobs: counting by localization with point supervision. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 547\u2013562 (2018)","DOI":"10.1007\/978-3-030-01216-8_34"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, X., Chen, D.: Csrnet: dilated convolutional neural networks for understanding the highly congested scenes. In: CVPR, pp. 1091\u20131100 (2018)","DOI":"10.1109\/CVPR.2018.00120"},{"key":"2_CR17","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.: Focal inverse distance transform maps for crowd localization. IEEE Trans. Multimedia 25, 6040\u20136052 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Lin, W., Chan, A.B.: Optimal transport minimization: crowd localization on density maps for semi-supervised counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21663\u201321673 (2023)","DOI":"10.1109\/CVPR52729.2023.02075"},{"key":"2_CR19","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\/CVF International Conference on Computer Vision, pp. 1676\u20131685 (2023)","DOI":"10.1109\/ICCV51070.2023.00161"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhao, Q., Ma, Y., Dai, F.: Bipartite matching for crowd counting with point supervision. In: IJCAI, pp. 860\u2013866 (2021)","DOI":"10.24963\/ijcai.2021\/119"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Liu, W., Salzmann, M., Fua, P.: Context-aware crowd counting. In: CVPR, pp. 5099\u20135108 (2019)","DOI":"10.1109\/CVPR.2019.00524"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Ma, Z., Wei, X., Hong, X., Gong, Y.: Bayesian loss for crowd count estimation with point supervision. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6142\u20136151 (2019)","DOI":"10.1109\/ICCV.2019.00624"},{"key":"2_CR23","doi-asserted-by":"crossref","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, vol.\u00a035, pp. 2319\u20132327 (2021)","DOI":"10.1609\/aaai.v35i3.16332"},{"key":"2_CR24","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":"2_CR25","unstructured":"Peyr\u00e9, G., Cuturi, M., et\u00a0al.: Computational optimal transport. Center for Research in Economics and Statistics Working Papers (2017-86) (2017)"},{"key":"2_CR26","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/978-3-031-20080-9_40","volume-title":"ECCV 2022, Part X","author":"R Qiu","year":"2022","unstructured":"Qiu, R., Xu, M., Yan, Y., Smith, J.S., Yang, X.: 3D random occlusion and multi-layer projection for deep multi-camera pedestrian localization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part X. LNCS, vol. 13670, pp. 695\u2013710. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_40"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Sabzmeydani, P., Mori, G.: Detecting pedestrians by learning shapelet features. In: CVPR, pp.\u00a01\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383134"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Sam, D.B., Surya, S., Babu, R.V.: Switching convolutional neural network for crowd counting. In: CVPR, pp. 4031\u20134039 (2017)","DOI":"10.1109\/CVPR.2017.429"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Shi, M., Yang, Z., et\u00a0al.: Revisiting perspective information for efficient crowd counting. In: CVPR, pp. 7279\u20137288 (2019)","DOI":"10.1109\/CVPR.2019.00745"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Patel, V.M.: Generating high-quality crowd density maps using contextual pyramid CNNs. In: ICCV, pp. 1879\u20131888 (2017)","DOI":"10.1109\/ICCV.2017.206"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Song, L., Wu, J., Yang, M., Zhang, Q., Li, Y., Yuan, J.: Stacked homography transformations for multi-view pedestrian detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6049\u20136057 (2021)","DOI":"10.1109\/ICCV48922.2021.00599"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Song, Q., et al.: Rethinking counting and localization in crowds: a purely point-based framework. arXiv preprint arXiv:2107.12746 (2021)","DOI":"10.1109\/ICCV48922.2021.00335"},{"issue":"2","key":"2_CR33","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. Vision 57(2), 137\u2013154 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Wan, J., Liu, Z., Chan, A.B.: A generalized loss function for crowd counting and localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1974\u20131983 (2021)","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"2_CR35","unstructured":"Wang, B., Liu, H., Samaras, D., Nguyen, M.H.: Distribution matching for crowd counting. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1595\u20131607 (2020)"},{"issue":"2","key":"2_CR36","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s11263-006-0027-7","volume":"75","author":"B Wu","year":"2007","unstructured":"Wu, B., Nevatia, R.: Detection and tracking of multiple, partially occluded humans by Bayesian combination of edgelet based part detectors. Int. J. Comput. Vision 75(2), 247\u2013266 (2007)","journal-title":"Int. J. Comput. Vision"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Xu, Y., Liu, X., Liu, Y., Zhu, S.C.: Multi-view people tracking via hierarchical trajectory composition. In: CVPR, pp. 4256\u20134265 (2016)","DOI":"10.1109\/CVPR.2016.461"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Yan, S., et al.: Multiview transformers for video recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3333\u20133343 (2022)","DOI":"10.1109\/CVPR52688.2022.00333"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Yan, Z., et al.: Perspective-guided convolution networks for crowd counting. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 952\u2013961 (2019)","DOI":"10.1109\/ICCV.2019.00104"},{"key":"2_CR40","doi-asserted-by":"crossref","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4374\u20134383 (2020)","DOI":"10.1109\/CVPR42600.2020.00443"},{"key":"2_CR41","unstructured":"Zhang, C., Li, H., et\u00a0al.: Cross-scene crowd counting via deep convolutional neural networks. In: CVPR, pp. 833\u2013841 (2015)"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Chan, A.B.: Wide-area crowd counting via ground-plane density maps and multi-view fusion CNNs. In: CVPR, pp. 8297\u20138306 (2019)","DOI":"10.1109\/CVPR.2019.00849"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Lin, W., Chan, A.B.: Cross-view cross-scene multi-view crowd counting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 557\u2013567 (2021)","DOI":"10.1109\/CVPR46437.2021.00062"},{"key":"2_CR44","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73235-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:14:46Z","timestamp":1732828486000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73235-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732348","9783031732355"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73235-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}