{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T20:15:33Z","timestamp":1788466533815,"version":"build-2803163510"},"reference-count":35,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372153"],"award-info":[{"award-number":["62372153"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2308085MF216"],"award-info":[{"award-number":["2308085MF216"]}],"id":[{"id":"10.13039\/501100003995","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":[[2026,10]]},"DOI":"10.1016\/j.patrec.2026.07.032","type":"journal-article","created":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T15:03:34Z","timestamp":1785251014000},"page":"143-149","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["VP-MonoMF: Visual prompt guided monocular 3D object detection with multiscale fusion"],"prefix":"10.1016","volume":"208","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8646-8426","authenticated-orcid":false,"given":"Ye","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9833-5684","authenticated-orcid":false,"given":"Jun","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weihua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patrec.2026.07.032_bib0001","series-title":"Proceedings of the 33rd ACM International Conference on Multimedia","first-page":"2294","article-title":"Multimodal decomposed distillation with instance alignment and uncertainty compensation for thermal object detection","author":"Liu","year":"2025"},{"key":"10.1016\/j.patrec.2026.07.032_bib0002","first-page":"1","article-title":"Dual-perspective alignment learning for multimodal remote sensing object detection","volume":"63","author":"Liu","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patrec.2026.07.032_bib0003","doi-asserted-by":"crossref","first-page":"1909","DOI":"10.1007\/s11263-023-01790-1","article-title":"3D object detection for autonomous driving: a comprehensive survey","volume":"131","author":"Mao","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.patrec.2026.07.032_bib0004","doi-asserted-by":"crossref","first-page":"3123","DOI":"10.1109\/TITS.2020.2981737","article-title":"A multilayer pyramid network based on learning for vehicle logo recognition","volume":"22","author":"Yu","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patrec.2026.07.032_bib0005","doi-asserted-by":"crossref","first-page":"2054","DOI":"10.11834\/jig.220122","article-title":"RIC-NVNet: night-time vehicle enhancement network for vehicle model recognition","volume":"28","author":"Ye","year":"2023","journal-title":"J. Image Graph."},{"issue":"1","key":"10.1016\/j.patrec.2026.07.032_bib0006","doi-asserted-by":"crossref","DOI":"10.2174\/18744478-v16-e2208191","article-title":"Deep 3D dynamic object detection towards successful and safe navigation for full autonomous driving","volume":"16","author":"Wijesekara","year":"2022","journal-title":"Open Transp. J."},{"key":"10.1016\/j.patrec.2026.07.032_bib0007","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16923","article-title":"Decoupled pseudo-labeling for semi-supervised monocular 3D object detection","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patrec.2026.07.032_bib0008","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10248","article-title":"MonoCD: monocular 3D object detection with complementary depths","author":"Yan","year":"2024"},{"key":"10.1016\/j.patrec.2026.07.032_bib0009","first-page":"72145","article-title":"Training an open-vocabulary monocular 3D object detection model without 3D data","volume":"2020","author":"Huang","year":"2024","journal-title":"Neural Inf. Process. Syst. Conf."},{"key":"10.1016\/j.patrec.2026.07.032_bib0010","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4289","article-title":"SMOKE: single-stage monocular 3D object detection via keypoint estimation","author":"Liu","year":"2020"},{"key":"10.1016\/j.patrec.2026.07.032_bib0011","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.patrec.2025.08.024","article-title":"LRTG3D: large receptive field 3D object detection with truncated Gaussian denoising query","volume":"197","author":"Li","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patrec.2026.07.032_bib0012","series-title":"European Conference on Computer Vision (ECCV)","article-title":"Fully test-time adaptation for monocular 3D object detection","author":"Lin","year":"2024"},{"issue":"6","key":"10.1016\/j.patrec.2026.07.032_bib0013","doi-asserted-by":"crossref","first-page":"9109","DOI":"10.1109\/TITS.2025.3541372","article-title":"Multi-scale grid attention and probabilistic refinement for accurate roi-based monocular 3D object detection","volume":"26","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.patrec.2026.07.032_bib0014","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"4842","article-title":"MonoPGC: monocular 3D object detection with pixel geometry contexts","author":"Wu","year":"2023"},{"key":"10.1016\/j.patrec.2026.07.032_bib0015","doi-asserted-by":"crossref","first-page":"11392","DOI":"10.52202\/079017-0362","article-title":"MonoMAE: enhancing monocular 3D detection through depth-aware masked autoencoders","volume":"2023","author":"Jiang","year":"2024","journal-title":"Neural Inf. Process. Syst."},{"key":"10.1016\/j.patrec.2026.07.032_bib0016","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"17482","article-title":"Weakly supervised monocular 3D object detection using multi-view projection and direction consistency","author":"Tao","year":"2023"},{"key":"10.1016\/j.patrec.2026.07.032_bib0017","series-title":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"16561","article-title":"UniMODE: unified monocular 3D object detection","author":"Li","year":"2024"},{"key":"10.1016\/j.patrec.2026.07.032_bib0018","series-title":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"6791","article-title":"MonoNeRD: NeRF-like representations for monocular 3D object detection","author":"Xu","year":"2023"},{"key":"10.1016\/j.patrec.2026.07.032_bib0019","doi-asserted-by":"crossref","first-page":"7464","DOI":"10.1109\/LRA.2023.3313053","article-title":"You only look bottom-up for monocular 3D object detection","volume":"8","author":"Xiong","year":"2024","journal-title":"IEEE Rob. Autom. Lett."},{"key":"10.1016\/j.patrec.2026.07.032_bib0020","series-title":"European Conference on Computer Vision (ECCV)","first-page":"123","article-title":"Lidar point cloud guided monocular 3D object detection","author":"Peng","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.032_bib0021","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2403","article-title":"Deep layer aggregation","author":"Yu","year":"2017"},{"key":"10.1016\/j.patrec.2026.07.032_bib0022","series-title":"AAAI Conference on Artificial Intelligence","first-page":"10478","article-title":"Monocular 3D object detection with decoupled structured polygon estimation and height-guided depth estimation","author":"Cai","year":"2020"},{"key":"10.1016\/j.patrec.2026.07.032_bib0023","doi-asserted-by":"crossref","first-page":"2033","DOI":"10.52202\/068431-0148","article-title":"Mogde: boosting mobile monocular 3D object detection with ground depth estimation","volume":"35","author":"Zhou","year":"2022","journal-title":"Neural Inf. Process. Syst."},{"key":"10.1016\/j.patrec.2026.07.032_bib0024","series-title":"2021 IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"15621","article-title":"AutoShape: real-time shape-aware monocular 3D object detection","author":"Liu","year":"2021"},{"key":"10.1016\/j.patrec.2026.07.032_bib0025","series-title":"European Conference on Computer Vision (ECCV)","first-page":"718","article-title":"Densely constrained depth estimator for monocular 3D object detection","author":"Li","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.032_bib0026","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"10374","article-title":"MonoRUn: monocular 3D object detection by reconstruction and uncertainty propagation","author":"Chen","year":"2021"},{"key":"10.1016\/j.patrec.2026.07.032_bib0027","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4002","article-title":"MonoDTR: monocular 3D object detection with depth-aware transformer","author":"Huang","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.032_bib0028","series-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"12090","article-title":"MonoPair: monocular 3D object detection using pairwise spatial relationships","author":"Chen","year":"2020"},{"key":"10.1016\/j.patrec.2026.07.032_bib0029","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4719","article-title":"Delving into localization errors for monocular 3D object detection","author":"Ma","year":"2021"},{"key":"10.1016\/j.patrec.2026.07.032_bib0030","series-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3288","article-title":"Objects are different: flexible monocular 3D object detection","author":"Zhang","year":"2021"},{"key":"10.1016\/j.patrec.2026.07.032_bib0031","series-title":"AAAI Conference on Artificial Intelligence","first-page":"1810","article-title":"Learning auxiliary monocular contexts helps monocular 3d object detection","volume":"36","author":"Liu","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.032_bib0032","series-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3783","article-title":"MonoGround: detecting monocular 3D objects from the ground","author":"Qin","year":"2022"},{"key":"10.1016\/j.patrec.2026.07.032_bib0033","series-title":"2023 IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"4270","article-title":"Multivariate probabilistic monocular 3D object detection","author":"Shi","year":"2023"},{"key":"10.1016\/j.patrec.2026.07.032_bib0034","article-title":"GRAMO: geometric resampling augmentation for monocular 3D object detection","volume":"18","author":"Guan","year":"2024","journal-title":"Front. J. Sci. Comput."},{"key":"10.1016\/j.patrec.2026.07.032_bib0035","series-title":"2012 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"3354","article-title":"Are we ready for autonomous driving? The KITTI vision benchmark suite","author":"Geiger","year":"2012"}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526002709?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865526002709?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T19:24:54Z","timestamp":1788463494000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865526002709"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":35,"alternative-id":["S0167865526002709"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2026.07.032","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VP-MonoMF: Visual prompt guided monocular 3D object detection with multiscale fusion","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2026.07.032","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Published by Elsevier B.V.","name":"copyright","label":"Copyright"}]}}