{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:58:33Z","timestamp":1782835113549,"version":"3.54.5"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T00:00:00Z","timestamp":1776124800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113755","type":"journal-article","created":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T13:12:15Z","timestamp":1776172335000},"page":"113755","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PB","title":["Count2Density: Crowd density estimation without location-level annotations"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4914-174X","authenticated-orcid":false,"given":"Mattia","family":"Litrico","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Pound","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sotirios A.","family":"Tsaftaris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastiano","family":"Battiato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mario Valerio","family":"Giuffrida","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113755_b1","article-title":"Learning to count objects in images","volume":"23","author":"Lempitsky","year":"2010","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113755_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107616","article-title":"Towards using count-level weak supervision for crowd counting","volume":"109","author":"Lei","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113755_b3","doi-asserted-by":"crossref","unstructured":"Y. Zhang, D. Zhou, S. Chen, S. Gao, Y. Ma, Single-Image Crowd Counting via Multi-Column Convolutional Neural Network, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2016, pp. 589\u2013597.","DOI":"10.1109\/CVPR.2016.70"},{"key":"10.1016\/j.patcog.2026.113755_b4","series-title":"Innovations and Advances in Cognitive Systems","first-page":"383","article-title":"Comprehensive study of various methods for estimating crowd density","author":"Jaiswal","year":"2024"},{"key":"10.1016\/j.patcog.2026.113755_b5","doi-asserted-by":"crossref","unstructured":"X. Liu, J. van de Weijer, A.D. Bagdanov, Leveraging Unlabeled Data for Crowd Counting by Learning to Rank, in: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 7661\u20137669.","DOI":"10.1109\/CVPR.2018.00799"},{"key":"10.1016\/j.patcog.2026.113755_b6","doi-asserted-by":"crossref","unstructured":"W. Liu, N. Durasov, P. Fua, Leveraging Self-Supervision for Cross-Domain Crowd Counting, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 5331\u20135342.","DOI":"10.1109\/CVPR52688.2022.00527"},{"key":"10.1016\/j.patcog.2026.113755_b7","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2893","article-title":"CrowdCLIP: Unsupervised crowd counting via vision-language model","author":"Liang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113755_b8","doi-asserted-by":"crossref","unstructured":"Z. Xiong, L. Chai, W. Liu, Y. Liu, S. Ren, S. He, Glance to count: Learning to rank with anchors for weakly-supervised crowd counting, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2024, pp. 343\u2013352.","DOI":"10.1109\/WACV57701.2024.00041"},{"key":"10.1016\/j.patcog.2026.113755_b9","doi-asserted-by":"crossref","unstructured":"Z. Ma, X. Wei, X. Hong, Y. Gong, Bayesian Loss for Crowd Count Estimation With Point Supervision, in: 2019 IEEE\/CVF International Conference on Computer Vision, ICCV, 2019, pp. 6141\u20136150.","DOI":"10.1109\/ICCV.2019.00624"},{"key":"10.1016\/j.patcog.2026.113755_b10","doi-asserted-by":"crossref","unstructured":"H. Lin, Z. Ma, R. Ji, Y. Wang, X. Hong, Boosting Crowd Counting via Multifaceted Attention, in: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 19596\u201319605.","DOI":"10.1109\/CVPR52688.2022.01901"},{"key":"10.1016\/j.patcog.2026.113755_b11","series-title":"Computer Vision \u2013 ECCV 2020","first-page":"242","article-title":"Semi-supervised crowd counting via self-training on surrogate tasks","author":"Liu","year":"2020"},{"key":"10.1016\/j.patcog.2026.113755_b12","series-title":"Computer Vision \u2013 ECCV 2020","first-page":"212","article-title":"Learning to count in the crowd from limited labeled data","author":"Sindagi","year":"2020"},{"key":"10.1016\/j.patcog.2026.113755_b13","doi-asserted-by":"crossref","unstructured":"S. Gong, S. Zhang, J. Yang, D. Dai, B. Schiele, Bi-Level Alignment for Cross-Domain Crowd Counting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 7542\u20137550.","DOI":"10.1109\/CVPR52688.2022.00739"},{"key":"10.1016\/j.patcog.2026.113755_b14","series-title":"Joint CNN and transformer network via weakly supervised learning for efficient crowd counting","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113755_b15","doi-asserted-by":"crossref","unstructured":"H. Idrees, M. Tayyab, K. Athrey, D. Zhang, S.A. Al-Maadeed, N.M. Rajpoot, M. Shah, Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds, in: European Conference on Computer Vision, 2018.","DOI":"10.1007\/978-3-030-01216-8_33"},{"key":"10.1016\/j.patcog.2026.113755_b16","first-page":"2594","article-title":"JHU-CROWD++: Large-scale crowd counting dataset and a benchmark method","volume":"44","author":"Sindagi","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113755_b17","doi-asserted-by":"crossref","first-page":"2633","DOI":"10.1109\/TMM.2021.3086709","article-title":"Crowd counting via perspective-guided fractional-dilation convolution","volume":"24","author":"Yan","year":"2021","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113755_b18","doi-asserted-by":"crossref","unstructured":"Y. Zhang, D. Zhou, S. Chen, S. Gao, Y. Ma, Single-image crowd counting via multi-column convolutional neural network, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 589\u2013597.","DOI":"10.1109\/CVPR.2016.70"},{"key":"10.1016\/j.patcog.2026.113755_b19","doi-asserted-by":"crossref","unstructured":"W. Liu, M. Salzmann, P. Fua, Context-aware crowd counting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5099\u20135108.","DOI":"10.1109\/CVPR.2019.00524"},{"key":"10.1016\/j.patcog.2026.113755_b20","doi-asserted-by":"crossref","unstructured":"S. Yang, W. Guo, Y. Ren, CrowdFormer: An Overlap Patching Vision Transformer for Top-Down Crowd Counting, in: International Joint Conference on Artificial Intelligence, 2022.","DOI":"10.24963\/ijcai.2022\/215"},{"key":"10.1016\/j.patcog.2026.113755_b21","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12809","article-title":"CrowdDiff: Multi-Hypothesis Crowd Density Estimation Using Diffusion Models","author":"Ranasinghe","year":"2024"},{"key":"10.1016\/j.patcog.2026.113755_b22","series-title":"Computer Vision \u2013 ECCV 2020","first-page":"565","article-title":"Active crowd counting with limited supervision","author":"Zhao","year":"2020"},{"key":"10.1016\/j.patcog.2026.113755_b23","doi-asserted-by":"crossref","unstructured":"Y. Xu, Z. Zhong, D. Lian, J. Li, Z. Li, X. Xu, S. Gao, Crowd Counting With Partial Annotations in an Image, in: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV, 2021, pp. 15550\u201315559.","DOI":"10.1109\/ICCV48922.2021.01528"},{"issue":"10","key":"10.1016\/j.patcog.2026.113755_b24","doi-asserted-by":"crossref","DOI":"10.3390\/jimaging7100198","article-title":"Semi-supervised domain adaptation for holistic counting under label gap","volume":"7","author":"Litrico","year":"2021","journal-title":"J. Imaging"},{"key":"10.1016\/j.patcog.2026.113755_b25","series-title":"Computer Vision \u2013 ECCV 2020","first-page":"1","article-title":"Weakly-supervised crowd counting learns from sorting rather than locations","author":"Yang","year":"2020"},{"key":"10.1016\/j.patcog.2026.113755_b26","series-title":"Mixture of counting CNNs: Adaptive integration of CNNs specialized to specific appearance for crowd counting","author":"Kumagai","year":"2017"},{"issue":"6","key":"10.1016\/j.patcog.2026.113755_b27","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-021-3445-y","article-title":"Transcrowd: weakly-supervised crowd counting with transformers","volume":"65","author":"Liang","year":"2022","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.patcog.2026.113755_b28","series-title":"DivideMix: Learning with noisy labels as semi-supervised learning","author":"Li","year":"2020"},{"issue":"3","key":"10.1016\/j.patcog.2026.113755_b29","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1109\/TPAMI.2014.2345401","article-title":"Global contrast Based Salient Region detection","volume":"37","author":"Cheng","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113755_b30","doi-asserted-by":"crossref","unstructured":"P. Zhang, D. Wang, H. Lu, H. Wang, X. Ruan, Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection, in: 2017 IEEE International Conference on Computer Vision, ICCV, 2017, pp. 202\u2013211.","DOI":"10.1109\/ICCV.2017.31"},{"key":"10.1016\/j.patcog.2026.113755_b31","doi-asserted-by":"crossref","unstructured":"X. Qin, Z. Zhang, C. Huang, C. Gao, M. Dehghan, M. Jagersand, BASNet: Boundary-Aware Salient Object Detection, in: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2019, pp. 7471\u20137481.","DOI":"10.1109\/CVPR.2019.00766"},{"key":"10.1016\/j.patcog.2026.113755_b32","series-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"10.1016\/j.patcog.2026.113755_b33","article-title":"NWPU-crowd: A large-scale benchmark for crowd counting and localization","author":"Wang","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113755_b34","first-page":"3386","article-title":"Modeling noisy annotations for crowd counting","volume":"vol. 33","author":"Wan","year":"2020"},{"key":"10.1016\/j.patcog.2026.113755_b35","doi-asserted-by":"crossref","unstructured":"J. Wan, Z. Liu, A.B. Chan, A Generalized Loss Function for Crowd Counting and Localization, in: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 1974\u20131983.","DOI":"10.1109\/CVPR46437.2021.00201"},{"key":"10.1016\/j.patcog.2026.113755_b36","series-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","article-title":"Unsupervised data augmentation for consistency training","author":"Xie","year":"2020"},{"key":"10.1016\/j.patcog.2026.113755_b37","series-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","first-page":"1195","article-title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","author":"Tarvainen","year":"2017"},{"key":"10.1016\/j.patcog.2026.113755_b38","series-title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","first-page":"3635","article-title":"Interpolation consistency training for semi-supervised learning","author":"Verma","year":"2019"},{"key":"10.1016\/j.patcog.2026.113755_b39","doi-asserted-by":"crossref","unstructured":"C. LI, X. Hu, S. Abousamra, C. Chen, Calibrating Uncertainty for Semi-Supervised Crowd Counting, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2023, pp. 16731\u201316741.","DOI":"10.1109\/ICCV51070.2023.01534"},{"key":"10.1016\/j.patcog.2026.113755_b40","doi-asserted-by":"crossref","unstructured":"T. Han, J. Gao, Y. Yuan, Q. Wang, Focus on Semantic Consistency for Cross-Domain Crowd Understanding, in: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2020, pp. 1848\u20131852.","DOI":"10.1109\/ICASSP40776.2020.9054768"},{"key":"10.1016\/j.patcog.2026.113755_b41","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7640","article-title":"Guiding pseudo-labels with uncertainty estimation for source-free unsupervised domain adaptation","author":"Litrico","year":"2023"},{"key":"10.1016\/j.patcog.2026.113755_b42","doi-asserted-by":"crossref","unstructured":"Han, et al., STEERER: Resolving Scale Variations for Counting and Localization via Selective Inheritance Learning, in: ICCV, 2023.","DOI":"10.1109\/ICCV51070.2023.01997"},{"key":"10.1016\/j.patcog.2026.113755_b43","series-title":"Robust unsupervised crowd counting and localization with adaptive resolution SAM","author":"Wan","year":"2024"},{"key":"10.1016\/j.patcog.2026.113755_b44","article-title":"Texture-guided saliency distilling for unsupervised salient object detection","author":"Zhou","year":"2023","journal-title":"CVPR"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600720X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600720X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T21:12:11Z","timestamp":1781298731000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S003132032600720X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":44,"alternative-id":["S003132032600720X"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113755","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Count2Density: Crowd density estimation without location-level annotations","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113755","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113755"}}