{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T22:35:26Z","timestamp":1782772526503,"version":"3.54.5"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197680","type":"print"},{"value":"9783031197697","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-19769-7_3","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T11:40:06Z","timestamp":1666438806000},"page":"38-54","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":140,"title":["An End-to-End Transformer Model for\u00a0Crowd Localization"],"prefix":"10.1007","author":[{"given":"Dingkang","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"3_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 (2021)","DOI":"10.1609\/aaai.v35i2.16170"},{"key":"3_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"issue":"1","key":"3_CR3","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1109\/JBHI.2021.3105545","volume":"26","author":"Y Chen","year":"2021","unstructured":"Chen, Y., Liang, D., Bai, X., Xu, Y., Yang, X.: Cell localization and counting using direction field map. IEEE J. Biomed. Health Inf. 26(1), 359\u2013368 (2021)","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"3_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: Proceedings of International Conference on Learning Representations (2020)"},{"key":"3_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1007\/978-3-030-66823-5_41","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"D Du","year":"2020","unstructured":"Du, D., et al.: VisDrone-CC2020: the vision meets drone crowd counting challenge results. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12538, pp. 675\u2013691. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-66823-5_41"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Gao, J., Gong, M., Li, X.: Congested crowd instance localization with dilated convolutional swin transformer. arXiv preprint arXiv:2108.00584 (2021)","DOI":"10.1016\/j.neucom.2022.09.113"},{"key":"3_CR7","unstructured":"Gao, J., Han, T., Wang, Q., Yuan, Y.: Domain-adaptive crowd counting via inter-domain features segregation and gaussian-prior reconstruction. arXiv preprint arXiv:1912.03677 (2019)"},{"key":"3_CR8","unstructured":"Gao, J., Han, T., Yuan, Y., Wang, Q.: Learning independent instance maps for crowd localization. arXiv preprint arXiv:2012.04164 (2020)"},{"key":"3_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neucom.2019.08.018","volume":"363","author":"J Gao","year":"2019","unstructured":"Gao, J., Wang, Q., Yuan, Y.: Scar: spatial-\/channel-wise attention regression networks for crowd counting. Neurocomputing 363, 1\u20138 (2019)","journal-title":"Neurocomputing"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Hu, P., Ramanan, D.: Finding tiny faces. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.166"},{"key":"3_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1007\/978-3-030-58542-6_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Hu","year":"2020","unstructured":"Hu, Y., et al.: NAS-count: counting-by-density with neural architecture search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 747\u2013766. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_45"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Idrees, H., et al.: Composition loss for counting, density map estimation and localization in dense crowds. In: Proceedings of European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01216-8_33"},{"issue":"1\u20132","key":"3_CR14","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1\u20132), 83\u201397 (1955)","journal-title":"Naval Res. Logist. Q."},{"key":"3_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 European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01216-8_34"},{"key":"3_CR16","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 IEEE International Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00120"},{"issue":"6","key":"3_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-021-3445-y","volume":"65","author":"D Liang","year":"2022","unstructured":"Liang, D., Chen, X., Xu, W., Zhou, Y., Bai, X.: Transcrowd: weakly-supervised crowd counting with transformers. Sci. China Inf. Sci. 65(6), 1\u201314 (2022)","journal-title":"Sci. China Inf. Sci."},{"key":"3_CR18","unstructured":"Liang, D., Xu, W., Zhu, Y., Zhou, Y.: Focal inverse distance transform maps for crowd localization and counting in dense crowd. arXiv preprint arXiv:2102.07925 (2021)"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Liu, C., Weng, X., Mu, Y.: Recurrent attentive zooming for joint crowd counting and precise localization. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00131"},{"key":"3_CR20","doi-asserted-by":"crossref","unstructured":"Liu, L., Lu, H., Zou, H., Xiong, H., Cao, Z., Shen, C.: Weighing counts: sequential crowd counting by reinforcement learning. In: Proceedings of European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58607-2_10"},{"key":"3_CR21","doi-asserted-by":"crossref","unstructured":"Liu, L., Qiu, Z., Li, G., Liu, S., Ouyang, W., Lin, L.: Crowd counting with deep structured scale integration network. In: Proceedings of IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00186"},{"key":"3_CR22","doi-asserted-by":"crossref","unstructured":"Liu, W., Salzmann, M., Fua, P.: Context-aware crowd counting. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00524"},{"key":"3_CR23","doi-asserted-by":"publisher","first-page":"5427","DOI":"10.1109\/TIP.2022.3195321","volume":"31","author":"X Liu","year":"2022","unstructured":"Liu, X., et al.: End-to-end temporal action detection with transformer. IEEE Trans. Image Process. 31, 5427\u20135441 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., Shi, M., Zhao, Q., Wang, X.: Point in, box out: beyond counting persons in crowds. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00663"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of IEEE International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Visdrone-cc2021: the vision meets drone crowd counting challenge results. In: Proceedings of IEEE International Conference on Computer Vision, pp. 2830\u20132838 (2021)","DOI":"10.1109\/ICCVW54120.2021.00317"},{"key":"3_CR27","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 IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00624"},{"key":"3_CR28","doi-asserted-by":"crossref","unstructured":"Meng, D., et al.: Conditional detr for fast training convergence. In: Proceedings of IEEE International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"3_CR29","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Proceedings of Advances in Neural Information Processing Systems (2015)"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Ribera, J., G\u00fcera, D., Chen, Y., Delp, E.J.: Locating objects without bounding boxes. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00664"},{"key":"3_CR31","first-page":"2739","volume":"43","author":"DB Sam","year":"2020","unstructured":"Sam, D.B., Peri, S.V., Sundararaman, M.N., Kamath, A., Radhakrishnan, V.B.: Locate, size and count: accurately resolving people in dense crowds via detection. IEEE Trans. Pattern Anal. Mach. Intell. 43, 2739\u20132751 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR32","doi-asserted-by":"crossref","unstructured":"Sindagi, V.A., Patel, V.M.: Multi-level bottom-top and top-bottom feature fusion for crowd counting. In: Proceedings of IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00109"},{"key":"3_CR33","first-page":"2594","volume":"44","author":"VA Sindagi","year":"2020","unstructured":"Sindagi, V.A., Yasarla, R., Patel, V.M.: Jhu-crowd++: large-scale crowd counting dataset and a benchmark method. IEEE Trans. Pattern Anal. Mach. Intell. 44, 2594\u20132609 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR34","doi-asserted-by":"crossref","unstructured":"Song, Q., et al.: Rethinking counting and localization in crowds: a purely point-based framework. In: Proceedings of IEEE International Conference on Computer Vision, pp. 3365\u20133374 (2021)","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"3_CR35","unstructured":"Sun, G., Liu, Y., Probst, T., Paudel, D.P., Popovic, N., Van Gool, L.: Boosting crowd counting with transformers. arXiv preprint arXiv:2105.10926 (2021)"},{"key":"3_CR36","unstructured":"Tian, Y., Chu, X., Wang, H.: Cctrans: simplifying and improving crowd counting with transformer. arXiv preprint arXiv:2109.14483 (2021)"},{"key":"3_CR37","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: Proceedings of International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"3_CR38","first-page":"3386","volume":"33","author":"J Wan","year":"2020","unstructured":"Wan, J., Chan, A.: Modeling noisy annotations for crowd counting. Adv. Neural Inf. Process. Syst. 33, 3386\u20133396 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3_CR39","doi-asserted-by":"crossref","unstructured":"Wan, J., Liu, Z., Chan, A.B.: A generalized loss function for crowd counting and localization. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1974\u20131983 (2021)","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"3_CR40","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.: Kernel-based density map generation for dense object counting. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1357\u20131370 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR41","unstructured":"Wang, B., Liu, H., Samaras, D., Hoai, M.: Distribution matching for crowd counting. In: Proceedings of Advances in Neural Information Processing Systems (2020)"},{"key":"3_CR42","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.: Nwpu-crowd: a large-scale benchmark for crowd counting and localization. IEEE Trans. Pattern Anal. Mach. Intell. 43, 2141\u20132149 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Q., Gao, J., Lin, W., Yuan, Y.: Learning from synthetic data for crowd counting in the wild. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00839"},{"key":"3_CR44","doi-asserted-by":"publisher","first-page":"2876","DOI":"10.1109\/TIP.2021.3055632","volume":"30","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Hou, J., Hou, X., Chau, L.P.: A self-training approach for point-supervised object detection and counting in crowds. IEEE Trans. Image Process. 30, 2876\u20132887 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"3_CR45","doi-asserted-by":"crossref","unstructured":"Wen, L., et al.: Detection, tracking, and counting meets drones in crowds: a benchmark. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 7812\u20137821 (2021)","DOI":"10.1109\/CVPR46437.2021.00772"},{"key":"3_CR46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11263-021-01542-z","volume":"130","author":"C Xu","year":"2022","unstructured":"Xu, C., et al.: Autoscale: learning to scale for crowd counting. Int. J. Comput. Vision 130, 1\u201330 (2022)","journal-title":"Int. J. Comput. Vision"},{"key":"3_CR47","doi-asserted-by":"crossref","unstructured":"Xu, C., Qiu, K., Fu, J., Bai, S., Xu, Y., Bai, X.: Learn to scale: generating multipolar normalized density map for crowd counting. In: Proceedings of IEEE International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00847"},{"key":"3_CR48","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 IEEE International Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.70"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19769-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T13:55:39Z","timestamp":1710338139000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19769-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197680","9783031197697"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19769-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}