{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T04:12:44Z","timestamp":1778731964635,"version":"3.51.4"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["021714380026"],"award-info":[{"award-number":["021714380026"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BE2022138"],"award-info":[{"award-number":["BE2022138"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011246","name":"State Key Laboratory of Novel Software Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011246","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072232"],"award-info":[{"award-number":["62072232"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008048","name":"Nanjing University","doi-asserted-by":"publisher","award":["ZZKT2024B20"],"award-info":[{"award-number":["ZZKT2024B20"]}],"id":[{"id":"10.13039\/501100008048","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.patrec.2026.04.006","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:58:34Z","timestamp":1775782714000},"page":"100-106","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Thermal crowd counting by distilling multi-modal knowledge"],"prefix":"10.1016","volume":"204","author":[{"given":"Xiaoxu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Shi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8111-7339","authenticated-orcid":false,"given":"Ruichao","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tongwei","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.patrec.2026.04.006_bib0001","first-page":"1595","article-title":"Distribution matching for crowd counting","volume":"33","author":"Wang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patrec.2026.04.006_bib0002","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1974","article-title":"A generalized loss function for crowd counting and localization","author":"Wan","year":"2021"},{"key":"10.1016\/j.patrec.2026.04.006_bib0003","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.patrec.2017.07.007","article-title":"A survey of recent advances in cnn-based single image crowd counting and density estimation","volume":"107","author":"Sindagi","year":"2018","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.04.006_bib0004","series-title":"Twelfth International Conference on Digital Image Processing","first-page":"323","article-title":"Privacy aware crowd-counting using thermal cameras","volume":"11519","author":"Tse","year":"2020"},{"issue":"1","key":"10.1016\/j.patrec.2026.04.006_bib0005","doi-asserted-by":"crossref","first-page":"29","DOI":"10.21608\/mjeer.2022.218777","article-title":"An improved technique for crowd counting based on thermal bands","volume":"31","author":"Hassan","year":"2022","journal-title":"Menoufia J. Electron. Eng. Res."},{"key":"10.1016\/j.patrec.2026.04.006_bib0006","series-title":"2022 IEEE International Symposium on Circuits and Systems","first-page":"3299","article-title":"TafNet: a three-stream adaptive fusion network for rgb-t crowd counting","author":"Tang","year":"2022"},{"key":"10.1016\/j.patrec.2026.04.006_bib0007","first-page":"1","article-title":"RGB-T multi-modal crowd counting based on transformer","author":"Liu","year":"2022","journal-title":"British Mach. Vis. Conf."},{"key":"10.1016\/j.patrec.2026.04.006_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4823","article-title":"Cross-modal collaborative representation learning and a large-scale rgbt benchmark for crowd counting","author":"Liu","year":"2021"},{"key":"10.1016\/j.patrec.2026.04.006_bib0009","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"90","article-title":"Spatio-channel attention blocks for cross-modal crowd counting","author":"Zhang","year":"2022"},{"key":"10.1016\/j.patrec.2026.04.006_bib0010","series-title":"2022 IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"Multimodal crowd counting with mutual attention transformers","author":"Wu","year":"2022"},{"issue":"12","key":"10.1016\/j.patrec.2026.04.006_bib0011","doi-asserted-by":"crossref","first-page":"24540","DOI":"10.1109\/TITS.2022.3203385","article-title":"DEFNet: dual-branch enhanced feature fusion network for RGB-T crowd counting","volume":"23","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patrec.2026.04.006_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106885","article-title":"CGINet: cross-modality grade interaction network for RGB-T crowd counting","volume":"126","author":"Pan","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"5","key":"10.1016\/j.patrec.2026.04.006_bib0013","doi-asserted-by":"crossref","first-page":"4156","DOI":"10.1109\/TITS.2023.3321328","article-title":"MC 3 net: multimodality cross-guided compensation coordination network for RGB-T crowd counting","volume":"25","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patrec.2026.04.006_bib0014","series-title":"Proceedings of the 2024 International Conference on Multimedia Retrieval","first-page":"570","article-title":"Semantic-guided RGB-thermal crowd counting with segment anything model","author":"Fang","year":"2024"},{"key":"10.1016\/j.patrec.2026.04.006_bib0015","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1016\/j.patrec.2019.02.026","article-title":"Depth information guided crowd counting for complex crowd scenes","volume":"125","author":"Xu","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.04.006_bib0016","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2025.3622207","article-title":"AllSpark: a multimodal spatio-temporal general intelligence model with ten modalities via language as a reference framework","volume":"63","author":"Shao","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patrec.2026.04.006_bib0017","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"20039","article-title":"MMaNet: margin-aware distillation and modality-aware regularization for incomplete multimodal learning","author":"Wei","year":"2023"},{"key":"10.1016\/j.patrec.2026.04.006_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7257","article-title":"Texture-guided saliency distilling for unsupervised salient object detection","author":"Zhou","year":"2023"},{"key":"10.1016\/j.patrec.2026.04.006_bib0019","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2827","article-title":"Cross modal distillation for supervision transfer","author":"Gupta","year":"2016"},{"key":"10.1016\/j.patrec.2026.04.006_bib0020","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5213","article-title":"Multimodal distillation for egocentric action recognition","author":"Radevski","year":"2023"},{"key":"10.1016\/j.patrec.2026.04.006_bib0021","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"7460","article-title":"SimdiStill: simulated multi-modal distillation for bev 3d object detection","volume":"38","author":"Zhao","year":"2024"},{"key":"10.1016\/j.patrec.2026.04.006_bib0022","series-title":"Proceedings of the Asian Conference on Computer Vision","article-title":"RGB-T crowd counting from drone: a benchmark and mmccn network","author":"Peng","year":"2020"},{"key":"10.1016\/j.patrec.2026.04.006_bib0023","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6142","article-title":"Bayesian loss for crowd count estimation with point supervision","author":"Ma","year":"2019"},{"key":"10.1016\/j.patrec.2026.04.006_bib0024","unstructured":"G. Hinton, O. Vinyals, J. Dean, Distilling the knowledge in a neural network,(2015) arXiv: 1503.02531."},{"key":"10.1016\/j.patrec.2026.04.006_bib0025","article-title":"DSKFuse: passive-active distillation learning for multi-modal image fusion via dynamic sparse kansformer","author":"Ding","year":"2025","journal-title":"Expert Syst. Appl."},{"issue":"11","key":"10.1016\/j.patrec.2026.04.006_bib0026","doi-asserted-by":"crossref","first-page":"20327","DOI":"10.1109\/JIOT.2024.3369642","article-title":"MJPNet-S*: multistyle joint-perception network with knowledge distillation for drone RGB-thermal crowd density estimation in smart cities","volume":"11","author":"Zhou","year":"2024","journal-title":"IEEE Internet Things J."},{"issue":"19","key":"10.1016\/j.patrec.2026.04.006_bib0027","doi-asserted-by":"crossref","first-page":"31758","DOI":"10.1109\/JIOT.2024.3420449","article-title":"Visual prompt multibranch fusion network for RGB-thermal crowd counting","volume":"11","author":"Mu","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.patrec.2026.04.006_bib0028","series-title":"European Conference on Computer Vision","first-page":"231","article-title":"Multi-modal crowd counting via a broker modality","author":"Meng","year":"2024"},{"issue":"12","key":"10.1016\/j.patrec.2026.04.006_bib0029","doi-asserted-by":"crossref","first-page":"12477","DOI":"10.1109\/TCSVT.2025.3588815","article-title":"A mutual head knowledge distillation framework for lightweight RGB-T crowd counting","volume":"35","author":"Mu","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"18","key":"10.1016\/j.patrec.2026.04.006_bib0030","doi-asserted-by":"crossref","first-page":"37928","DOI":"10.1109\/JIOT.2025.3584795","article-title":"LRANet: lightweight relation-aware network based on self-comparative distillation for UAV RGB-thermal crowd counting in smart cities","volume":"12","author":"Yang","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"3","key":"10.1016\/j.patrec.2026.04.006_bib0031","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"PVT v2: improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Comput. Visual Med."},{"key":"10.1016\/j.patrec.2026.04.006_bib0032","series-title":"International Conference on Learning Representations","article-title":"Deformable detr: deformable transformers for end-to-end object detection","author":"Zhu","year":"2021"},{"key":"10.1016\/j.patrec.2026.04.006_bib0033","series-title":"In International Conference on Learning Representations","article-title":"FitNets: hints for thin deep nets","author":"Romero","year":"2015"},{"key":"10.1016\/j.patrec.2026.04.006_bib0034","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"23756","article-title":"Enhanced training of query-based object detection via selective query recollection","author":"Chen","year":"2023"},{"key":"10.1016\/j.patrec.2026.04.006_bib0035","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6898","article-title":"Detrdistill: a universal knowledge distillation framework for detr-families","author":"Chang","year":"2023"},{"key":"10.1016\/j.patrec.2026.04.006_bib0036","first-page":"1","article-title":"BGDFNet: bidirectional gated and dynamic fusion network for RGB-T crowd counting in smart city system","volume":"73","author":"Xie","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.patrec.2026.04.006_bib0037","first-page":"1","article-title":"MMFFNet: multi-modal feature fusion network for RGB-T crowd counting","volume":"74","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.patrec.2026.04.006_bib0038","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"734","article-title":"Scale aggregation network for accurate and efficient crowd counting","author":"Cao","year":"2018"},{"key":"10.1016\/j.patrec.2026.04.006_bib0039","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1091","article-title":"CSRNet: dilated convolutional neural networks for understanding the highly congested scenes","author":"Li","year":"2018"},{"issue":"3","key":"10.1016\/j.patrec.2026.04.006_bib0040","doi-asserted-by":"crossref","first-page":"2358","DOI":"10.1109\/TIV.2022.3217261","article-title":"Instance, scale, and teacher adaptive knowledge distillation for visual detection in autonomous driving","volume":"8","author":"Lan","year":"2022","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.patrec.2026.04.006_bib0041","first-page":"1","article-title":"Adaptive knowledge distillation for lightweight remote sensing object detectors optimizing","volume":"60","author":"Yang","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patrec.2026.04.006_bib0042","series-title":"Iberian Conference on Pattern Recognition and Image Analysis","first-page":"423","article-title":"Extremely overlapping vehicle counting","author":"Guerrero-G\u00f3mez-Olmedo","year":"2015"},{"issue":"9","key":"10.1016\/j.patrec.2026.04.006_bib0043","doi-asserted-by":"crossref","first-page":"15808","DOI":"10.1109\/TITS.2022.3145476","article-title":"Thermal infrared image colorization for nighttime driving scenes with top-down guided attention","volume":"23","author":"Luo","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526001273?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526001273?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T03:31:08Z","timestamp":1778729468000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865526001273"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":43,"alternative-id":["S0167865526001273"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.04.006","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Thermal crowd counting by distilling multi-modal knowledge","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.04.006","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}]}}