{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T12:59:58Z","timestamp":1789477198256,"version":"build-2803163510"},"reference-count":61,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007765","name":"Shenyang Municipal Bureau of Science and Technology","doi-asserted-by":"publisher","award":["23-503-6-18"],"award-info":[{"award-number":["23-503-6-18"]}],"id":[{"id":"10.13039\/501100007765","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007620","name":"Department of Education of Liaoning Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007620","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Displays"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.displa.2026.103480","type":"journal-article","created":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T08:19:07Z","timestamp":1775895547000},"page":"103480","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["MonoGATR: Monocular 3D object detection with a geometry-aware transformer"],"prefix":"10.1016","volume":"94","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5511-5851","authenticated-orcid":false,"given":"Chuanlong","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4661-0424","authenticated-orcid":false,"given":"Chao","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3948-6952","authenticated-orcid":false,"given":"Hongming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4731-829X","authenticated-orcid":false,"given":"Yufeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.displa.2026.103480_b1","doi-asserted-by":"crossref","DOI":"10.1109\/TITS.2024.3439557","article-title":"Robustness-aware 3d object detection in autonomous driving: A review and outlook","author":"Song","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"8","key":"10.1016\/j.displa.2026.103480_b2","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":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.displa.2026.103480_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.108796","article-title":"3D object detection for autonomous driving: A survey","volume":"130","author":"Qian","year":"2022","journal-title":"Pattern Recognit."},{"issue":"5","key":"10.1016\/j.displa.2026.103480_b4","doi-asserted-by":"crossref","first-page":"3537","DOI":"10.1109\/TPAMI.2023.3346386","article-title":"3D object detection from images for autonomous driving: a survey","volume":"46","author":"Ma","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.displa.2026.103480_b5","doi-asserted-by":"crossref","first-page":"3322","DOI":"10.1109\/TRO.2024.3400831","article-title":"Toward robust robot 3-d perception in urban environments: The ut campus object dataset","volume":"40","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Robot."},{"key":"10.1016\/j.displa.2026.103480_b6","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"2029","article-title":"Mutual information-calibrated conformal feature fusion for uncertainty-aware multimodal 3d object detection at the edge","author":"Stutts","year":"2024"},{"issue":"1","key":"10.1016\/j.displa.2026.103480_b7","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.displa.2026.103480_b8","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."},{"issue":"12","key":"10.1016\/j.displa.2026.103480_b9","doi-asserted-by":"crossref","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","article-title":"Deep learning for 3d point clouds: A survey","volume":"43","author":"Guo","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"10.1016\/j.displa.2026.103480_b10","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","article-title":"Pct: Point cloud transformer","volume":"7","author":"Guo","year":"2021","journal-title":"Comput. Vis. Media"},{"key":"10.1016\/j.displa.2026.103480_b11","doi-asserted-by":"crossref","DOI":"10.1109\/LRA.2025.3544487","article-title":"MonoSG: Monocular 3D object detection with stereo guidance","author":"Fan","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.displa.2026.103480_b12","article-title":"Bevformer: learning bird\u2019s-eye-view representation from lidar-camera via spatiotemporal transformers","author":"Li","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"8","key":"10.1016\/j.displa.2026.103480_b13","doi-asserted-by":"crossref","first-page":"3962","DOI":"10.1109\/TCSVT.2023.3237579","article-title":"Pseudo-mono for monocular 3D object detection in autonomous driving","volume":"33","author":"Tao","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.displa.2026.103480_b14","doi-asserted-by":"crossref","first-page":"10421","DOI":"10.52202\/068431-0757","article-title":"Bevfusion: A simple and robust lidar-camera fusion framework","volume":"35","author":"Liang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.displa.2026.103480_b15","doi-asserted-by":"crossref","unstructured":"Y. Xie, C. Xu, M.-J. Rakotosaona, P. Rim, F. Tombari, K. Keutzer, M. Tomizuka, W. Zhan, Sparsefusion: Fusing multi-modal sparse representations for multi-sensor 3d object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 17591\u201317602.","DOI":"10.1109\/ICCV51070.2023.01613"},{"key":"10.1016\/j.displa.2026.103480_b16","series-title":"European Conference on Computer Vision","first-page":"664","article-title":"Deviant: Depth equivariant network for monocular 3d object detection","author":"Kumar","year":"2022"},{"key":"10.1016\/j.displa.2026.103480_b17","doi-asserted-by":"crossref","unstructured":"K.-C. Huang, T.-H. Wu, H.-T. Su, W.H. Hsu, Monodtr: Monocular 3d object detection with depth-aware transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4012\u20134021.","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"10.1016\/j.displa.2026.103480_b18","doi-asserted-by":"crossref","unstructured":"L. Yan, P. Yan, S. Xiong, X. Xiang, Y. Tan, Monocd: Monocular 3d object detection with complementary depths, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 10248\u201310257.","DOI":"10.1109\/CVPR52733.2024.00976"},{"key":"10.1016\/j.displa.2026.103480_b19","doi-asserted-by":"crossref","unstructured":"Z. Liu, Z. Wu, R. T\u00f3th, Smoke: Single-stage monocular 3d object detection via keypoint estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 996\u2013997.","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"10.1016\/j.displa.2026.103480_b20","doi-asserted-by":"crossref","unstructured":"X. Ma, Y. Zhang, D. Xu, D. Zhou, S. Yi, H. Li, W. Ouyang, Delving into localization errors for monocular 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 4721\u20134730.","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"10.1016\/j.displa.2026.103480_b21","doi-asserted-by":"crossref","unstructured":"Y. Lu, X. Ma, L. Yang, T. Zhang, Y. Liu, Q. Chu, J. Yan, W. Ouyang, Geometry uncertainty projection network for monocular 3d object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 3111\u20133121.","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"10.1016\/j.displa.2026.103480_b22","first-page":"1810","article-title":"Learning auxiliary monocular contexts helps monocular 3d object detection","volume":"vol. 36","author":"Liu","year":"2022"},{"key":"10.1016\/j.displa.2026.103480_b23","doi-asserted-by":"crossref","unstructured":"Y. Zhang, J. Lu, J. Zhou, Objects are different: Flexible monocular 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3289\u20133298.","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"10.1016\/j.displa.2026.103480_b24","doi-asserted-by":"crossref","unstructured":"M. Zhu, L. Ge, P. Wang, H. Peng, Monoedge: Monocular 3d object detection using local perspectives, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 643\u2013652.","DOI":"10.1109\/WACV56688.2023.00071"},{"key":"10.1016\/j.displa.2026.103480_b25","doi-asserted-by":"crossref","unstructured":"G. Brazil, X. Liu, M3d-rpn: Monocular 3d region proposal network for object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 9287\u20139296.","DOI":"10.1109\/ICCV.2019.00938"},{"key":"10.1016\/j.displa.2026.103480_b26","doi-asserted-by":"crossref","unstructured":"X. Shi, Q. Ye, X. Chen, C. Chen, Z. Chen, T.-K. Kim, Geometry-based distance decomposition for monocular 3d object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 15172\u201315181.","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"10.1016\/j.displa.2026.103480_b27","doi-asserted-by":"crossref","unstructured":"X. Shi, Z. Chen, T.-K. Kim, Multivariate probabilistic monocular 3D object detection, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2023, pp. 4281\u20134290.","DOI":"10.1109\/WACV56688.2023.00426"},{"key":"10.1016\/j.displa.2026.103480_b28","doi-asserted-by":"crossref","unstructured":"C. Reading, A. Harakeh, J. Chae, S.L. Waslander, Categorical depth distribution network for monocular 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 8555\u20138564.","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"10.1016\/j.displa.2026.103480_b29","series-title":"European Conference on Computer Vision","first-page":"718","article-title":"Densely constrained depth estimator for monocular 3d object detection","author":"Li","year":"2022"},{"key":"10.1016\/j.displa.2026.103480_b30","doi-asserted-by":"crossref","unstructured":"Z. Liu, D. Zhou, F. Lu, J. Fang, L. Zhang, Autoshape: Real-time shape-aware monocular 3d object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 15641\u201315650.","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"10.1016\/j.displa.2026.103480_b31","series-title":"Monopgc: Monocular 3d object detection with pixel geometry contexts","author":"Wu","year":"2023"},{"key":"10.1016\/j.displa.2026.103480_b32","doi-asserted-by":"crossref","unstructured":"Q. Lian, P. Li, X. Chen, Monojsg: Joint semantic and geometric cost volume for monocular 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 1070\u20131079.","DOI":"10.1109\/CVPR52688.2022.00114"},{"key":"10.1016\/j.displa.2026.103480_b33","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.displa.2026.103480_b34","doi-asserted-by":"crossref","unstructured":"R. Zhang, H. Qiu, T. Wang, Z. Guo, Z. Cui, Y. Qiao, H. Li, P. Gao, MonoDETR: Depth-guided transformer for monocular 3D object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 9155\u20139166.","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"10.1016\/j.displa.2026.103480_b35","article-title":"MonoTrans: Long-range contextual dependency transformer for monocular 3D object detection","author":"Li","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"issue":"1","key":"10.1016\/j.displa.2026.103480_b36","doi-asserted-by":"crossref","first-page":"3475","DOI":"10.1109\/TCE.2024.3353530","article-title":"Monoli: Precise monocular 3-d object detection for next-generation consumer electronics for autonomous electric vehicles","volume":"70","author":"Gao","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.displa.2026.103480_b37","first-page":"10478","article-title":"Monocular 3d object detection with decoupled structured polygon estimation and height-guided depth estimation","volume":"vol. 34","author":"Cai","year":"2020"},{"key":"10.1016\/j.displa.2026.103480_b38","doi-asserted-by":"crossref","unstructured":"M. Ding, Y. Huo, H. Yi, Z. Wang, J. Shi, Z. Lu, P. Luo, Learning depth-guided convolutions for monocular 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 1000\u20131001.","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"10.1016\/j.displa.2026.103480_b39","doi-asserted-by":"crossref","unstructured":"L. Wang, L. Du, X. Ye, Y. Fu, G. Guo, X. Xue, J. Feng, L. Zhang, Depth-conditioned dynamic message propagation for monocular 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 454\u2013463.","DOI":"10.1109\/CVPR46437.2021.00052"},{"issue":"3","key":"10.1016\/j.displa.2026.103480_b40","doi-asserted-by":"crossref","first-page":"1327","DOI":"10.1109\/LRA.2023.3238137","article-title":"Opa-3d: Occlusion-aware pixel-wise aggregation for monocular 3d object detection","volume":"8","author":"Su","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.displa.2026.103480_b41","series-title":"European Conference on Computer Vision","first-page":"71","article-title":"Did-m3d: Decoupling instance depth for monocular 3d object detection","author":"Peng","year":"2022"},{"key":"10.1016\/j.displa.2026.103480_b42","doi-asserted-by":"crossref","unstructured":"F. Manhardt, W. Kehl, A. Gaidon, Roi-10d: Monocular lifting of 2d detection to 6d pose and metric shape, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 2069\u20132078.","DOI":"10.1109\/CVPR.2019.00217"},{"key":"10.1016\/j.displa.2026.103480_b43","doi-asserted-by":"crossref","unstructured":"Z. Zou, X. Ye, L. Du, X. Cheng, X. Tan, L. Zhang, J. Feng, X. Xue, E. Ding, The devil is in the task: Exploiting reciprocal appearance-localization features for monocular 3d object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 2713\u20132722.","DOI":"10.1109\/ICCV48922.2021.00271"},{"key":"10.1016\/j.displa.2026.103480_b44","doi-asserted-by":"crossref","unstructured":"Y. Wang, W.-L. Chao, D. Garg, B. Hariharan, M. Campbell, K.Q. Weinberger, Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 8445\u20138453.","DOI":"10.1109\/CVPR.2019.00864"},{"key":"10.1016\/j.displa.2026.103480_b45","doi-asserted-by":"crossref","unstructured":"K. Duan, S. Bai, L. Xie, H. Qi, Q. Huang, Q. Tian, Centernet: Keypoint triplets for object detection, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 6569\u20136578.","DOI":"10.1109\/ICCV.2019.00667"},{"key":"10.1016\/j.displa.2026.103480_b46","first-page":"6189","article-title":"Fd3d: Exploiting foreground depth map for feature-supervised monocular 3d object detection","volume":"vol. 38","author":"Wu","year":"2024"},{"key":"10.1016\/j.displa.2026.103480_b47","doi-asserted-by":"crossref","first-page":"11703","DOI":"10.52202\/075280-0514","article-title":"Monouni: A unified vehicle and infrastructure-side monocular 3d object detection network with sufficient depth clues","volume":"36","author":"Jinrang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.displa.2026.103480_b48","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1109\/JAS.2023.123660","article-title":"Depth-guided vision transformer with normalizing flows for monocular 3D object detection","volume":"11","author":"Pan","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"10.1016\/j.displa.2026.103480_b49","series-title":"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.displa.2026.103480_b50","doi-asserted-by":"crossref","unstructured":"Y. Zhou, H. Zhu, Q. Liu, S. Chang, M. Guo, Monoatt: Online monocular 3d object detection with adaptive token transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 17493\u201317503.","DOI":"10.1109\/CVPR52729.2023.01678"},{"key":"10.1016\/j.displa.2026.103480_b51","first-page":"8851","article-title":"Monogrnet: A geometric reasoning network for monocular 3d object localization","volume":"vol. 33","author":"Qin","year":"2019"},{"key":"10.1016\/j.displa.2026.103480_b52","series-title":"Orthographic feature transform for monocular 3d object detection","author":"Roddick","year":"2018"},{"key":"10.1016\/j.displa.2026.103480_b53","doi-asserted-by":"crossref","unstructured":"Y. Chen, L. Tai, K. Sun, M. Li, Monopair: Monocular 3d object detection using pairwise spatial relationships, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 12093\u201312102.","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"10.1016\/j.displa.2026.103480_b54","doi-asserted-by":"crossref","unstructured":"F. Pu, Y. Wang, J. Deng, W. Yang, Monodgp: Monocular 3d object detection with decoupled-query and geometry-error priors, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 6520\u20136530.","DOI":"10.1109\/CVPR52734.2025.00611"},{"key":"10.1016\/j.displa.2026.103480_b55","doi-asserted-by":"crossref","unstructured":"B.-W. Yin, J.-L. Cao, M.-M. Cheng, Q. Hou, Dformerv2: Geometry self-attention for rgbd semantic segmentation, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 19345\u201319355.","DOI":"10.1109\/CVPR52734.2025.01802"},{"key":"10.1016\/j.displa.2026.103480_b56","series-title":"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.displa.2026.103480_b57","doi-asserted-by":"crossref","unstructured":"S. Ettinger, S. Cheng, B. Caine, C. Liu, H. Zhao, S. Pradhan, Y. Chai, B. Sapp, C.R. Qi, Y. Zhou, et al., Large scale interactive motion forecasting for autonomous driving: The waymo open motion dataset, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 9710\u20139719.","DOI":"10.1109\/ICCV48922.2021.00957"},{"key":"10.1016\/j.displa.2026.103480_b58","article-title":"3D object proposals for accurate object class detection","volume":"28","author":"Chen","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.displa.2026.103480_b59","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.displa.2026.103480_b60","series-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"10.1016\/j.displa.2026.103480_b61","series-title":"2024 International Conference on 3D Vision (3DV)","first-page":"1125","article-title":"Monolss: Learnable sample selection for monocular 3d detection","author":"Li","year":"2024"}],"container-title":["Displays"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0141938226001435?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0141938226001435?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T00:14:33Z","timestamp":1780877673000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0141938226001435"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":61,"alternative-id":["S0141938226001435"],"URL":"https:\/\/doi.org\/10.1016\/j.displa.2026.103480","relation":{},"ISSN":["0141-9382"],"issn-type":[{"value":"0141-9382","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MonoGATR: Monocular 3D object detection with a geometry-aware transformer","name":"articletitle","label":"Article Title"},{"value":"Displays","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.displa.2026.103480","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":"103480"}}