{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T04:58:33Z","timestamp":1790485113042,"version":"4.1.0"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,2,1]],"date-time":"2027-02-01T00:00:00Z","timestamp":1801440000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Signal Processing"],"published-print":{"date-parts":[[2027,2]]},"DOI":"10.1016\/j.sigpro.2026.110856","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:06:08Z","timestamp":1785510368000},"page":"110856","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MonoCAP: Coordinate-aware and perspective-aware learning for roadside monocular 3D object detection"],"prefix":"10.1016","volume":"251","author":[{"given":"Changhui","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiguo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yansong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"10","key":"10.1016\/j.sigpro.2026.110856_bib0001","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3729420","article-title":"A survey of autonomous driving from a deep learning perspective","volume":"57","author":"Zhao","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.sigpro.2026.110856_bib0002","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2024.109619","article-title":"Enhancing autonomous driving safety: a robust traffic sign detection and recognition model TSD-YOLO","volume":"225","author":"Zhao","year":"2024","journal-title":"Signal Process."},{"key":"10.1016\/j.sigpro.2026.110856_bib0003","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2023.109343","article-title":"A multi-sensor fusion framework with tight coupling for precise positioning and optimization","volume":"217","author":"Xia","year":"2024","journal-title":"Signal Process."},{"key":"10.1016\/j.sigpro.2026.110856_bib0004","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2021.108242","article-title":"Hybrid cooperative localization based on robot-sensor networks","volume":"188","author":"Liu","year":"2021","journal-title":"Signal Process."},{"key":"10.1016\/j.sigpro.2026.110856_bib0005","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"135","article-title":"Kinematic 3D object detection in monocular video","author":"Brazil","year":"2020"},{"key":"10.1016\/j.sigpro.2026.110856_bib0006","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9155","article-title":"MonoDETR: depth-guided transformer for monocular 3D object detection","author":"Zhang","year":"2023"},{"key":"10.1016\/j.sigpro.2026.110856_bib0007","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9287","article-title":"M3D-RPN: monocular 3D region proposal network for object detection","author":"Brazil","year":"2019"},{"key":"10.1016\/j.sigpro.2026.110856_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4721","article-title":"Delving into localization errors for monocular 3D object detection","author":"Ma","year":"2021"},{"issue":"11","key":"10.1016\/j.sigpro.2026.110856_bib0009","doi-asserted-by":"crossref","first-page":"17587","DOI":"10.1109\/TITS.2024.3412759","article-title":"MonoGAE: roadside monocular 3D object detection with ground-aware embeddings","volume":"25","author":"Yang","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"3","key":"10.1016\/j.sigpro.2026.110856_bib0010","doi-asserted-by":"crossref","first-page":"2020","DOI":"10.1109\/TPAMI.2024.3515454","article-title":"BEVFormer: learning bird\u2019s-eye-view representation from lidar-camera via spatiotemporal transformers","volume":"47","author":"Li","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.sigpro.2026.110856_bib0011","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1477","article-title":"BEVDepth: acquisition of reliable depth for multi-view 3D object detection","volume":"37","author":"Li","year":"2023"},{"key":"10.1016\/j.sigpro.2026.110856_bib0012","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21611","article-title":"BEVHeight: a robust framework for vision-based roadside 3D object detection","author":"Yang","year":"2023"},{"key":"10.1016\/j.sigpro.2026.110856_bib0013","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21361","article-title":"DAIR-V2X: a large-scale dataset for vehicle-infrastructure cooperative 3D object detection","author":"Yu","year":"2022"},{"key":"10.1016\/j.sigpro.2026.110856_bib0014","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21341","article-title":"Rope3D: the roadside perception dataset for autonomous driving and monocular 3D object detection task","author":"Ye","year":"2022"},{"key":"10.1016\/j.sigpro.2026.110856_bib0015","first-page":"1","article-title":"MonoPSTR: monocular 3-D object detection with dynamic position and scale-aware transformer","volume":"73","author":"Yang","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.sigpro.2026.110856_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12697","article-title":"PointPillars: fast encoders for object detection from point clouds","author":"Lang","year":"2019"},{"issue":"10","key":"10.1016\/j.sigpro.2026.110856_bib0017","doi-asserted-by":"crossref","first-page":"3337","DOI":"10.3390\/s18103337","article-title":"Second: sparsely embedded convolutional detection","volume":"18","author":"Yan","year":"2018","journal-title":"Sensors"},{"key":"10.1016\/j.sigpro.2026.110856_bib0018","series-title":"Proceedings of the 2019 IEEE International Conference on Robotics and Automation","first-page":"7276","article-title":"MVX-Net: multimodal voxelnet for 3D object detection","author":"Sindagi","year":"2019"},{"key":"10.1016\/j.sigpro.2026.110856_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2023.109165","article-title":"A comparative review on multi-modal sensors fusion based on deep learning","volume":"213","author":"Tang","year":"2023","journal-title":"Signal Process."},{"key":"10.1016\/j.sigpro.2026.110856_bib0020","doi-asserted-by":"crossref","DOI":"10.1016\/j.sigpro.2025.110271","article-title":"PDNet: pluralistic depth-aware network for RGB-D salient object detection","volume":"239","author":"Wei","year":"2026","journal-title":"Signal Process."},{"key":"10.1016\/j.sigpro.2026.110856_bib0021","series-title":"Proceedings of the 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.sigpro.2026.110856_bib0022","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4012","article-title":"MonoDTR: monocular 3D object detection with depth-aware transformer","author":"Huang","year":"2022"},{"key":"10.1016\/j.sigpro.2026.110856_bib0023","series-title":"Proceedings of the 2022 IEEE Intelligent Vehicles Symposium","first-page":"411","article-title":"DST3D: DLA-swin transformer for single-stage monocular 3D object detection","author":"Wu","year":"2022"},{"key":"10.1016\/j.sigpro.2026.110856_bib0024","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"},{"issue":"1","key":"10.1016\/j.sigpro.2026.110856_bib0025","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1109\/TIV.2023.3311949","article-title":"SSD-monodetr: supervised scale-aware deformable transformer for monocular 3D object detection","volume":"9","author":"He","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.sigpro.2026.110856_bib0026","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12093","article-title":"MonoPair: monocular 3D object detection using pairwise spatial relationships","author":"Chen","year":"2020"},{"key":"10.1016\/j.sigpro.2026.110856_bib0027","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"11669","article-title":"Learning depth-guided convolutions for monocular 3D object detection","author":"Ding","year":"2020"},{"key":"10.1016\/j.sigpro.2026.110856_bib0028","series-title":"Proceedings of the Conference on Computer Vision and Pattern Recognition","first-page":"6520","article-title":"MonoDGP: monocular 3D object detection with decoupled-query and geometry-error priors","author":"Pu","year":"2025"},{"key":"10.1016\/j.sigpro.2026.110856_bib0029","series-title":"Proceedings of the Advances in Neural Information Processing Systems","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.sigpro.2026.110856_bib0030","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, J. Dai, Deformable DETR: Deformable transformers for end-to-end object detection, 2020, arXiv preprint arXiv: 2010.04159."},{"key":"10.1016\/j.sigpro.2026.110856_bib0031","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3621","article-title":"Fast convergence of detr with spatially modulated co-attention","author":"Gao","year":"2021"},{"key":"10.1016\/j.sigpro.2026.110856_bib0032","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"3651","article-title":"Conditional DETR for fast training convergence","author":"Meng","year":"2021"},{"key":"10.1016\/j.sigpro.2026.110856_bib0033","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2567","article-title":"Anchor DETR: query design for transformer-based detector","volume":"vol. 36","author":"Wang","year":"2022"},{"key":"10.1016\/j.sigpro.2026.110856_bib0034","unstructured":"S. Liu, F. Li, H. Zhang, X. Yang, X. Qi, H. Su, L. Zhang, DAB-DETR: Dynamic anchor boxes are better queries for DETR, 2022, arXiv preprint arXiv: 2201.12329."},{"key":"10.1016\/j.sigpro.2026.110856_bib0035","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.sigpro.2026.110856_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16965","article-title":"Detrs beat yolos on real-time object detection","author":"Zhao","year":"2024"},{"key":"10.1016\/j.sigpro.2026.110856_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"10.1016\/j.sigpro.2026.110856_bib0038","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"390","article-title":"CSPNet: a new backbone that can enhance learning capability of CNN","author":"Wang","year":"2020"},{"key":"10.1016\/j.sigpro.2026.110856_bib0039","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2980","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"10.1016\/j.sigpro.2026.110856_bib0040","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"1991","article-title":"Disentangling monocular 3D object detection","author":"Simonelli","year":"2019"},{"key":"10.1016\/j.sigpro.2026.110856_bib0041","series-title":"Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3354","article-title":"Are we ready for autonomous driving? the kitti vision benchmark suite","author":"Geiger","year":"2012"},{"key":"10.1016\/j.sigpro.2026.110856_bib0042","unstructured":"I. Loshchilov, F. Hutter, Decoupled weight decay regularization, 2017, arXiv preprint arXiv: 1711.05101."},{"key":"10.1016\/j.sigpro.2026.110856_bib0043","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"2397","article-title":"ImVoxelNet: image to voxels projection for monocular and multi-view general-purpose 3D object detection","author":"Rukhovich","year":"2022"},{"issue":"6","key":"10.1016\/j.sigpro.2026.110856_bib0044","doi-asserted-by":"crossref","first-page":"5094","DOI":"10.1109\/TPAMI.2025.3549711","article-title":"BEVHeight++: toward robust visual centric 3D object detection","volume":"47","author":"Yang","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.sigpro.2026.110856_bib0045","doi-asserted-by":"crossref","first-page":"5424","DOI":"10.1109\/TIP.2024.3463409","article-title":"CoBEV: elevating roadside 3D object detection with depth and height complementarity","volume":"33","author":"Shi","year":"2024","journal-title":"IEEE Trans. Image Process."}],"container-title":["Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0165168426003695?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0165168426003695?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T04:36:19Z","timestamp":1790483779000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0165168426003695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,2]]},"references-count":45,"alternative-id":["S0165168426003695"],"URL":"https:\/\/doi.org\/10.1016\/j.sigpro.2026.110856","relation":{},"ISSN":["0165-1684"],"issn-type":[{"value":"0165-1684","type":"print"}],"subject":[],"published":{"date-parts":[[2027,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MonoCAP: Coordinate-aware and perspective-aware learning for roadside monocular 3D object detection","name":"articletitle","label":"Article Title"},{"value":"Signal Processing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.sigpro.2026.110856","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"}],"article-number":"110856"}}