{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T02:02:29Z","timestamp":1780020149057,"version":"3.53.1"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100017596","name":"Natural Science Basic Research Program of Shaanxi Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100015401","name":"Shaanxi Province Key Research and Development Projects","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015401","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Knowledge-Based Systems"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.knosys.2026.116255","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T19:36:43Z","timestamp":1779305803000},"page":"116255","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["RERF-net: Rotation-equivariant enhancement and refined fusion network for multi-modal 3D detection"],"prefix":"10.1016","volume":"346","author":[{"given":"Di","family":"Tian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4322-3258","authenticated-orcid":false,"given":"Jiabo","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.knosys.2026.116255_bib0001","doi-asserted-by":"crossref","first-page":"3781","DOI":"10.1109\/TIV.2023.3264658","article-title":"Multi-modal 3D object detection in autonomous driving: a survey and taxonomy","volume":"8","author":"Wang","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.knosys.2026.116255_bib0002","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Progressive bird's eye view perception for safety-critical autonomous driving: a comprehensive survey","author":"Gong","year":"2025"},{"key":"10.1016\/j.knosys.2026.116255_bib0003","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"BEVNeXt: reviving dense BEV frameworks for 3D object detection","author":"Li","year":"2023"},{"key":"10.1016\/j.knosys.2026.116255_bib0004","series-title":"Proceedings of the IEEE International Conference on Robotics and Automation","first-page":"4628","article-title":"Hdmap net: an online head map construction and evaluation frame work","author":"Li","year":"2022"},{"key":"10.1016\/j.knosys.2026.116255_bib0005","series-title":"Proceedings of the IEEE Winter Conference on Applications of Computer Vision","first-page":"1526","article-title":"CenterFusion: center-based radar and camera fusion for 3D object detection","author":"Nabati","year":"2021"},{"key":"10.1016\/j.knosys.2026.116255_bib0006","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"},{"key":"10.1016\/j.knosys.2026.116255_bib0007","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1090","article-title":"TransFusion: robust LiDAR-camera fusion for 3D object detection with transformers","author":"Bai","year":"2022"},{"key":"10.1016\/j.knosys.2026.116255_bib0008","article-title":"TiGDistill-BEV: multi-view BEV 3D object detection via target inner-geometry learning distillation","author":"Xu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116255_bib0009","series-title":"Proceedings of European Conference on Computer Vision","first-page":"719","article-title":"3D-CVF: generating joint camera and LiDAR features using cross-view spatial feature fusion for 3D object detection","author":"Yoo","year":"2020"},{"issue":"5","key":"10.1016\/j.knosys.2026.116255_bib0010","doi-asserted-by":"crossref","first-page":"2868","DOI":"10.3390\/s23052868","article-title":"PointPainting: 3D object detection aided by semantic image information","volume":"23","author":"Gao","year":"2023","journal-title":"Sensors"},{"key":"10.1016\/j.knosys.2026.116255_bib0011","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6378","article-title":"PointAugment: an auto-augmentation framework for Point cloud classification","author":"Li","year":"2020"},{"key":"10.1016\/j.knosys.2026.116255_bib0012","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121811","article-title":"Object feedback and feature information retention for small object detection in intelligent transportation scenes","volume":"238","author":"Tian","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.knosys.2026.116255_bib0013","series-title":"Proceedings of the Conference on Neural Information Processing Systems","first-page":"2336","article-title":"MVP: multimodal virtual point 3D detection","author":"Yin","year":"2021"},{"key":"10.1016\/j.knosys.2026.116255_bib0014","first-page":"1617","article-title":"SparseFusion: dynamic Human avatar modeling from sparse RGBD images","author":"Zuo","year":"2020","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.knosys.2026.116255_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.128886","article-title":"Multi-sensor information fusion in Internet of Vehicles based on deep learning","volume":"614","author":"Tian","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.knosys.2026.116255_bib0016","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"172","article-title":"FUTR3D: a unified sensor fusion framework for 3D detection","author":"Chen","year":"2023"},{"key":"10.1016\/j.knosys.2026.116255_bib0017","unstructured":"E. Xie, Z. Yu, D. Zhou, et al. M2BEV: multi-camera joint 3D detection and segmentation with unified birds-eye view representation, 2022. arXiv 2022, arXiv:2204.05088."},{"key":"10.1016\/j.knosys.2026.116255_bib0018","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"913","article-title":"FCOS3D: fully convolutional one-stage monocular 3D object detection","author":"Wang","year":"2021"},{"key":"10.1016\/j.knosys.2026.116255_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110085","article-title":"Dynamic graph transformer for 3D object detection","volume":"259","author":"Ren","year":"2023","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.knosys.2026.116255_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"PETRv2: a unified framework for 3D perception from multi-camera images","author":"Liu","year":"2022"},{"key":"10.1016\/j.knosys.2026.116255_bib0021","unstructured":"Y. Zhou, P. Sun, Y. Zhang, et al. End-to-End multi-view fusion for 3D object detection in LiDAR point clouds, 2019. arXiv 2019, arXiv:1910.06528."},{"key":"10.1016\/j.knosys.2026.116255_bib0022","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2147","article-title":"Monocular 3D object detection for autonomous driving","author":"Zhou","year":"2016"},{"key":"10.1016\/j.knosys.2026.116255_bib0023","series-title":"Proceedings of Conference on Robot Learning","first-page":"180","article-title":"DETR3D: 3D Object detection from multi-view images via 3D-to-2D queries","author":"Wang","year":"2022"},{"key":"10.1016\/j.knosys.2026.116255_bib0024","series-title":"Proceedings of European Conference on Computer Vision","first-page":"708","article-title":"BEVFormer: learning Bird's-eye-view representation from multi-camera images via Spatiotemporal Transformers","author":"Li","year":"2022"},{"key":"10.1016\/j.knosys.2026.116255_bib0025","unstructured":"J.J. Huang, G. Huang, Z. Zhu, et al. BEVDet: high-performance multi-camera 3D object detection in bird-eye-view, 2022. arXiv 2022, arXiv: 2112.11790."},{"key":"10.1016\/j.knosys.2026.116255_bib0026","series-title":"Proceedings of European Conference on Computer Vision","first-page":"531","article-title":"PETR: position embedding transformation for multi-view 3D object detection","author":"Liu","year":"2022"},{"key":"10.1016\/j.knosys.2026.116255_bib0027","unstructured":"J.J. Huang, G. Huang, BEVDet4D: exploit temporal cues in multi-camera 3D object detection, 2022. arXiv 2022, arXiv:2203.17054."},{"issue":"10","key":"10.1016\/j.knosys.2026.116255_bib0028","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.knosys.2026.116255_bib0029","doi-asserted-by":"crossref","first-page":"5036","DOI":"10.1109\/TCSVT.2023.3248656","article-title":"Balanced sample assignment and objective for single-model multi-class 3D object detection","volume":"33","author":"Xiao","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.knosys.2026.116255_bib0030","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"VoxelNeXt: fully sparse VoxelNet for 3D object detection and tracking","author":"Chen","year":"2023"},{"key":"10.1016\/j.knosys.2026.116255_bib0031","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1065","article-title":"Center-based 3D object detection and tracking","author":"Yin","year":"2021"},{"key":"10.1016\/j.knosys.2026.116255_bib0032","series-title":"Proceedings of the Winter Conference on Applications of Computer Vision","first-page":"772","article-title":"SparseBEV: high-performance sparse 3D object detection from multi-camera videos","author":"Liu","year":"2022"},{"key":"10.1016\/j.knosys.2026.116255_bib0033","series-title":"Proceedings of the Conference on Computer Vision and Pattern Recognition","first-page":"10529","article-title":"M3DETR: multi-representation, multi-scale, mutual-relation 3D object detection with transformers","author":"Guan","year":"2020"},{"key":"10.1016\/j.knosys.2026.116255_bib0034","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"918","article-title":"Frustum PointNet: deep learning for 3D object detection from RGB-D images","author":"Qi","year":"2018"},{"key":"10.1016\/j.knosys.2026.116255_bib0035","series-title":"Proceedings of the IEEE International Conference on Robotics and Automation","article-title":"MVX-net: multimodal VoxelNet for 3D object detection","author":"Vishwanath","year":"2019"},{"key":"10.1016\/j.knosys.2026.116255_bib0036","series-title":"Proceedings of the IEEE International Conference on Robotics and Automation","first-page":"10247","article-title":"BEVFusion: multi-task multi-sensor fusion with unified bird's-eye view representation","author":"Liu","year":"2023"},{"key":"10.1016\/j.knosys.2026.116255_bib0037","unstructured":"Y.P. Zhang, Z. Zhu, W.Z. Zheng, et al. BEVerse: unified perception and prediction in birds-eye-view for vision-centric autonomous driving, 2022. arXiv 2022, arXiv:2205.09743."},{"key":"10.1016\/j.knosys.2026.116255_bib0038","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2619","article-title":"GraphAlign: enhancing accurate feature alignment by graph matching for multi-modal 3D object detection","author":"Song","year":"2023"},{"key":"10.1016\/j.knosys.2026.116255_bib0039","first-page":"1","article-title":"VP-net: voxels as points for 3-D object detection","author":"Song","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.knosys.2026.116255_bib0040","article-title":"SAT-GCN: self-attention graph convolutional network-based 3D object detection for autonomous driving","author":"Wang","year":"2022","journal-title":"Knowl. Based. Syst."},{"key":"10.1016\/j.knosys.2026.116255_bib0041","article-title":"SparseDet: a simple and effective framework for fully sparse LiDAR-based 3D object detection","author":"Liu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.knosys.2026.116255_bib0042","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1109\/TIV.2024.3409684","article-title":"Fuzzy-NMS: improving 3D object detection with Fuzzy classification in NMS","volume":"10","author":"Wang","year":"2025","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.knosys.2026.116255_bib0043","article-title":"Multi-Sem Fusion: multimodal semantic fusion for 3-D object detection","author":"Xu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.knosys.2026.116255_bib0044","series-title":"Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"6246","article-title":"FGU3R: fine-grained fusion via unified 3D representation for multimodal 3D object detection","author":"Zhang","year":"2025"},{"key":"10.1016\/j.knosys.2026.116255_bib0045","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"7967","article-title":"SparseInteraction: sparse semantic guidance for radar and camera 3D object detection","author":"Jiang","year":"2024"},{"key":"10.1016\/j.knosys.2026.116255_bib0046","series-title":"Proceedings of the International Joint Conference on Artificial Intelligence","first-page":"1272","article-title":"RoboFusion: towards robust multi-modal 3D object detection via SAM","author":"Song","year":"2024"},{"key":"10.1016\/j.knosys.2026.116255_bib0047","first-page":"1","article-title":"LVP: leverage virtual points in multimodal early fusion for 3-D object detection","author":"Chen","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Knowledge-Based Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009810?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0950705126009810?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:13:15Z","timestamp":1780017195000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0950705126009810"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":47,"alternative-id":["S0950705126009810"],"URL":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116255","relation":{},"ISSN":["0950-7051"],"issn-type":[{"value":"0950-7051","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"RERF-net: Rotation-equivariant enhancement and refined fusion network for multi-modal 3D detection","name":"articletitle","label":"Article Title"},{"value":"Knowledge-Based Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.knosys.2026.116255","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":"116255"}}