{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T14:09:11Z","timestamp":1780495751074,"version":"3.54.1"},"reference-count":37,"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":[[2026,3,10]],"date-time":"2026-03-10T00:00:00Z","timestamp":1773100800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100010076","name":"Regional Council Provence-Alpes-Cote d'Azur","doi-asserted-by":"publisher","award":["2023\/2026 \\u2013 6688"],"award-info":[{"award-number":["2023\/2026 \\u2013 6688"]}],"id":[{"id":"10.13039\/501100010076","id-type":"DOI","asserted-by":"publisher"}]}],"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.2026.113436","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:15:58Z","timestamp":1773245758000},"page":"113436","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PA","title":["Multi-scale tiling for pseudo-labeling in dense scene object detection"],"prefix":"10.1016","volume":"179","author":[{"given":"Thi Quynh Khanh","family":"Dinh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9245-3407","authenticated-orcid":false,"given":"Nad\u00e9ge","family":"Thirion-Moreau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5646-8505","authenticated-orcid":false,"given":"Thanh Phuong","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3508-9565","authenticated-orcid":false,"given":"Jean-Jacques","family":"Simon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2033-1304","authenticated-orcid":false,"given":"Ludovic","family":"Escoubas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113436_bib0001","series-title":"European Conference on Computer Vision","first-page":"38","article-title":"Grounding dino: marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113436_bib0002","unstructured":"S. Shao, Z. Zhao, B. Li, T. Xiao, G. Yu, X. Zhang, J. Sun, Crowdhuman: A benchmark for detecting human in a crowd, (2018). arXiv preprint arXiv: 1805.00123."},{"key":"10.1016\/j.patcog.2026.113436_bib0003","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5227","article-title":"Precise detection in densely packed scenes","author":"Goldman","year":"2019"},{"key":"10.1016\/j.patcog.2026.113436_bib0004","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3124","article-title":"Cut and learn for unsupervised object detection and instance segmentation","author":"Wang","year":"2023"},{"issue":"1","key":"10.1016\/j.patcog.2026.113436_bib0005","first-page":"1","article-title":"Pascal VOC 2008 challenge","volume":"24","author":"Hoiem","year":"2009","journal-title":"World Literature Today"},{"key":"10.1016\/j.patcog.2026.113436_bib0006","series-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, Proceedings, Part v 13","first-page":"740","article-title":"Microsoft coco: common objects in context","author":"Lin","year":"2014"},{"issue":"6","key":"10.1016\/j.patcog.2026.113436_bib0007","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113436_bib0008","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.patcog.2026.113436_bib0009","series-title":"European Conference on Computer Vision","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.patcog.2026.113436_bib0010","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10598","article-title":"Instance-aware, context-focused, and memory-efficient weakly supervised object detection","author":"Ren","year":"2020"},{"key":"10.1016\/j.patcog.2026.113436_bib0011","article-title":"Localizing objects with self-supervised transformers and no labels","author":"Sim\u00e9oni","year":"2021","journal-title":"Proc. British Mach. Vision Conf. (BMVC)"},{"key":"10.1016\/j.patcog.2026.113436_bib0012","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113436_bib0013","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.patcog.2026.113436_bib0014","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113436_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110648","article-title":"Prompt-guided DETR with RoI-pruned masked attention for open-vocabulary object detection","volume":"155","author":"Song","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113436_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"0","article-title":"The power of tiling for small object detection","author":"Ozge Unel","year":"2019"},{"key":"10.1016\/j.patcog.2026.113436_bib0017","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6154","article-title":"Cascade r-cnn: delving into high quality object detection","author":"Cai","year":"2018"},{"key":"10.1016\/j.patcog.2026.113436_bib0018","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11\u201314, 2016, Proceedings, Part I 14","first-page":"21","article-title":"Ssd: single shot multibox detector","author":"Liu","year":"2016"},{"key":"10.1016\/j.patcog.2026.113436_bib0019","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.113436_bib0020","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6569","article-title":"Centernet: keypoint triplets for object detection","author":"Duan","year":"2019"},{"key":"10.1016\/j.patcog.2026.113436_bib0021","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"734","article-title":"Cornernet: detecting objects as paired keypoints","author":"Law","year":"2018"},{"key":"10.1016\/j.patcog.2026.113436_bib0022","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1007\/s11761-023-00361-z","article-title":"Densely packed object detection with transformer-based head and EM-merger","volume":"17","author":"Zhong","year":"2023","journal-title":"Service Oriented Comput. Appl."},{"issue":"4","key":"10.1016\/j.patcog.2026.113436_bib0023","article-title":"DS-YOLO: A dense small object detection algorithm based on inverted bottleneck and multi-scale fusion network","volume":"4","author":"Zhang","year":"2024","journal-title":"Biomimetic Intell. Rob."},{"key":"10.1016\/j.patcog.2026.113436_bib0024","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.131554","article-title":"End-to-end transformer-based detection with density-guided query selection for small objects","volume":"656","author":"Hoanh","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.113436_bib0025","series-title":"European Conference on Computer Vision","first-page":"728","article-title":"Simple open-vocabulary object detection","author":"Minderer","year":"2022"},{"key":"10.1016\/j.patcog.2026.113436_bib0026","unstructured":"H. Choi, Y. Lim, J. Shin, H. Shim, CoT-PL: Visual Chain-of-Thought Reasoning Meets Pseudo-Labeling for Open-Vocabulary Object Detection, (2025). arXiv preprint arXiv: 2510.14792."},{"key":"10.1016\/j.patcog.2026.113436_bib0027","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"issue":"12","key":"10.1016\/j.patcog.2026.113436_bib0028","doi-asserted-by":"crossref","first-page":"15790","DOI":"10.1109\/TPAMI.2023.3305122","article-title":"Tokencut: segmenting objects in images and videos with self-supervised transformer and normalized cut","volume":"45","author":"Wang","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"10.1016\/j.patcog.2026.113436_bib0029","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105379","article-title":"Enhancing few-shot object detection through pseudo-label mining","volume":"154","author":"Garcia-Fernandez","year":"2025","journal-title":"Image Vis Comput"},{"key":"10.1016\/j.patcog.2026.113436_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111428","article-title":"Self-supervised video object segmentation via pseudo label rectification","volume":"163","author":"Guo","year":"2025","journal-title":"Pattern Recognit"},{"key":"10.1016\/j.patcog.2026.113436_bib0031","series-title":"European Conference on Computer Vision","first-page":"334","article-title":"Crowd-sam: sam as a smart annotator for object detection in crowded scenes","author":"Cai","year":"2024"},{"key":"10.1016\/j.patcog.2026.113436_bib0032","series-title":"European Conference on Computer Vision","first-page":"478","article-title":"Robust zero-Shot crowd counting and localization with adaptive resolution SAM","author":"Wan","year":"2024"},{"key":"10.1016\/j.patcog.2026.113436_bib0033","doi-asserted-by":"crossref","first-page":"19769","DOI":"10.52202\/075280-0868","article-title":"Segment everything everywhere all at once","volume":"36","author":"Zou","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1\u20132","key":"10.1016\/j.patcog.2026.113436_bib0034","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/nav.3800020109","article-title":"The hungarian method for the assignment problem","volume":"2","author":"Kuhn","year":"1955","journal-title":"Naval Research Logistics Quart."},{"issue":"5","key":"10.1016\/j.patcog.2026.113436_bib0035","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.2026.113436_bib0036","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113436_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12214","article-title":"Detection in crowded scenes: one proposal, multiple predictions","author":"Chu","year":"2020"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004012?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326004012?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T13:10:29Z","timestamp":1780492229000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326004012"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":37,"alternative-id":["S0031320326004012"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113436","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":"Multi-scale tiling for pseudo-labeling in dense scene object detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113436","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113436"}}