{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T04:20:48Z","timestamp":1783052448888,"version":"3.54.6"},"reference-count":48,"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFD2000301"],"award-info":[{"award-number":["2023YFD2000301"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52394263"],"award-info":[{"award-number":["52394263"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U25A20379"],"award-info":[{"award-number":["U25A20379"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.imavis.2026.106048","type":"journal-article","created":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T06:31:07Z","timestamp":1780122667000},"page":"106048","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Occlusion-aware multi-modal 3D object detection via multi-stage cross-modal fusion"],"prefix":"10.1016","volume":"173","author":[{"given":"Weihua","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawei","family":"Pi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guodong","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2026.106048_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122836","article-title":"Autonomous driving system: A comprehensive survey","volume":"242","author":"Zhao","year":"2024","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"10.1016\/j.imavis.2026.106048_b2","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/TITS.2020.3012034","article-title":"Deep learning-based vehicle behavior prediction for autonomous driving applications: A review","volume":"23","author":"Mozaffari","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"12","key":"10.1016\/j.imavis.2026.106048_b3","doi-asserted-by":"crossref","first-page":"22772","DOI":"10.1109\/TITS.2022.3206235","article-title":"Survey on image and point-cloud fusion-based object detection in autonomous vehicles","volume":"23","author":"Peng","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"7","key":"10.1016\/j.imavis.2026.106048_b4","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.imavis.2026.106048_b5","series-title":"Robustness-aware 3D object detection in autonomous driving: A review and outlook","author":"Song","year":"2024"},{"key":"10.1016\/j.imavis.2026.106048_b6","series-title":"Progressive bird\u2019s eye view perception for safety-critical autonomous driving: A comprehensive survey","author":"Gong","year":"2025"},{"issue":"1208","key":"10.1016\/j.imavis.2026.106048_b7","article-title":"Progressive robustness-aware world models in autonomous driving: A review and outlook","volume":"2025","author":"Jia","year":"2025","journal-title":"TechRxiv"},{"issue":"16","key":"10.1016\/j.imavis.2026.106048_b8","doi-asserted-by":"crossref","first-page":"30255","DOI":"10.1109\/JSEN.2025.3582040","article-title":"Collaborative perception datasets for autonomous driving: A review","volume":"25","author":"Wang","year":"2025","journal-title":"IEEE Sensors J."},{"key":"10.1016\/j.imavis.2026.106048_b9","series-title":"ACM Multimedia 2024","article-title":"SparseInteraction: Sparse semantic guidance for radar and camera 3D object detection","author":"Jiang","year":"2024"},{"key":"10.1016\/j.imavis.2026.106048_b10","series-title":"GaussianPretrain: A simple unified 3D Gaussian representation for visual pre-training in autonomous driving","author":"Xu","year":"2024"},{"key":"10.1016\/j.imavis.2026.106048_b11","series-title":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22432","article-title":"Don\u2019t shake the wheel: Momentum-aware planning in end-to-end autonomous driving","author":"Song","year":"2025"},{"key":"10.1016\/j.imavis.2026.106048_b12","series-title":"DIVER: Reinforced diffusion breaks imitation bottlenecks in end-to-end autonomous driving","author":"Song","year":"2025"},{"key":"10.1016\/j.imavis.2026.106048_b13","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.neucom.2023.01.080","article-title":"Probabilistic instance shape reconstruction with sparse LiDAR for monocular 3D object detection","volume":"529","author":"Ji","year":"2023","journal-title":"Neurocomputing"},{"issue":"35","key":"10.1016\/j.imavis.2026.106048_b14","doi-asserted-by":"crossref","first-page":"83535","DOI":"10.1007\/s11042-024-18872-y","article-title":"YOLO-based object detection models: A review and its applications","volume":"83","author":"Vijayakumar","year":"2024","journal-title":"Multimedia Tools Appl."},{"issue":"9","key":"10.1016\/j.imavis.2026.106048_b15","doi-asserted-by":"crossref","first-page":"15898","DOI":"10.1109\/TITS.2022.3146271","article-title":"ID-YOLO: Real-time salient object detection based on the driver\u2019s fixation region","volume":"23","author":"Qin","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.imavis.2026.106048_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102429","article-title":"Fusion-driven deep feature network for enhanced object detection and tracking in video surveillance systems","volume":"109","author":"Jain","year":"2024","journal-title":"Inf. Fusion"},{"issue":"1","key":"10.1016\/j.imavis.2026.106048_b17","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1109\/TETCI.2020.3041019","article-title":"Granulated RCNN and multi-class deep SORT for multi-object detection and tracking","volume":"6","author":"Pramanik","year":"2022","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"issue":"3","key":"10.1016\/j.imavis.2026.106048_b18","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."},{"issue":"2","key":"10.1016\/j.imavis.2026.106048_b19","first-page":"1477","article-title":"BEVDepth: Acquisition of reliable depth for multi-view 3D object detection","volume":"37","author":"Li","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"6","key":"10.1016\/j.imavis.2026.106048_b20","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.imavis.2026.106048_b21","doi-asserted-by":"crossref","first-page":"5706","DOI":"10.1109\/TIP.2022.3201469","article-title":"3D cascade RCNN: High quality object detection in point clouds","volume":"31","author":"Cai","year":"2022","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"10.1016\/j.imavis.2026.106048_b22","doi-asserted-by":"crossref","first-page":"4069","DOI":"10.1109\/TIV.2023.3282567","article-title":"HYDRO-3D: Hybrid object detection and tracking for cooperative perception using 3D LiDAR","volume":"8","author":"Meng","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.imavis.2026.106048_b23","doi-asserted-by":"crossref","first-page":"2795","DOI":"10.1109\/TMM.2023.3304054","article-title":"SP-det: Leveraging saliency prediction for voxel-based 3D object detection in sparse point cloud","volume":"26","author":"An","year":"2024","journal-title":"IEEE Trans. Multimed."},{"issue":"6","key":"10.1016\/j.imavis.2026.106048_b24","doi-asserted-by":"crossref","first-page":"6074","DOI":"10.1109\/TITS.2023.3334873","article-title":"Exploiting label uncertainty for enhanced 3D object detection from point clouds","volume":"25","author":"Sun","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.imavis.2026.106048_b25","first-page":"1","article-title":"VP-net: Voxels as points for 3-D object detection","volume":"61","author":"Song","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.imavis.2026.106048_b26","first-page":"1","article-title":"SparseDet: A simple and effective framework for fully sparse LiDAR-based 3-D object detection","volume":"62","author":"Liu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.imavis.2026.106048_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2024.129144","article-title":"Investigating 3D object detection using stereo camera and LiDAR fusion with bird\u2019s-eye view representation","volume":"620","author":"Nie","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.imavis.2026.106048_b28","doi-asserted-by":"crossref","unstructured":"J. Yin, J. Shen, R. Chen, W. Li, R. Yang, P. Frossard, W. Wang, IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 14905\u201314915.","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"10.1016\/j.imavis.2026.106048_b29","series-title":"2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"6983","article-title":"Joint multi-object detection and tracking with camera-LiDAR fusion for autonomous driving","author":"Huang","year":"2021"},{"issue":"1","key":"10.1016\/j.imavis.2026.106048_b30","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1109\/TII.2023.3263274","article-title":"MVMM: Multiview multimodal 3-D object detection for autonomous driving","volume":"20","author":"Li","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.imavis.2026.106048_b31","first-page":"1","article-title":"KCDNet: Multimodal object detection in modal information imbalance scenes","volume":"73","author":"Wang","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.imavis.2026.106048_b32","series-title":"2023 IEEE International Conference on Robotics and Automation","first-page":"2774","article-title":"Bevfusion: Multi-task multi-sensor fusion with unified bird\u2019s-eye view representation","author":"Liu","year":"2023"},{"key":"10.1016\/j.imavis.2026.106048_b33","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"172","article-title":"FUTR3D: A unified sensor fusion framework for 3D detection","author":"Chen","year":"2023"},{"key":"10.1016\/j.imavis.2026.106048_b34","series-title":"2023 IEEE\/CVF International Conference on Computer Vision","first-page":"3335","article-title":"GraphAlign: Enhancing accurate feature alignment by graph matching for multi-modal 3D object detection","author":"Song","year":"2023"},{"issue":"4","key":"10.1016\/j.imavis.2026.106048_b35","doi-asserted-by":"crossref","first-page":"2619","DOI":"10.1109\/TCSVT.2023.3306361","article-title":"GraphAlign++: An accurate feature alignment by graph matching for multi-modal 3D object detection","volume":"34","author":"Song","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106048_b36","series-title":"Computer Vision \u2013 ECCV 2024","first-page":"347","article-title":"GraphBEV: Towards robust BEV feature alignment for multi-modal 3D object detection","author":"Song","year":"2025"},{"key":"10.1016\/j.imavis.2026.106048_b37","series-title":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"FGU3R: Fine-grained fusion via unified 3D representation for multimodal 3D object detection","author":"Zhang","year":"2025"},{"key":"10.1016\/j.imavis.2026.106048_b38","first-page":"1","article-title":"LVP: Leverage virtual points in multimodal early fusion for 3-D object detection","volume":"63","author":"Chen","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.imavis.2026.106048_b39","first-page":"1","article-title":"Multi-sem fusion: Multimodal semantic fusion for 3-D object detection","volume":"62","author":"Xu","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"1","key":"10.1016\/j.imavis.2026.106048_b40","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1109\/TCSVT.2025.3596322","article-title":"TiGDistill-BEV: Multi-view BEV 3D object detection via target inner-geometry learning distillation","volume":"36","author":"Xu","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106048_b41","series-title":"RoboFusion: Towards robust multi-modal 3D object detection via SAM","author":"Song","year":"2024"},{"key":"10.1016\/j.imavis.2026.106048_b42","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7354","article-title":"Sparse fuse dense: Towards high quality 3D detection with depth completion","author":"Wu","year":"2022"},{"key":"10.1016\/j.imavis.2026.106048_b43","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5632","article-title":"3D bounding box estimation using deep learning and geometry","author":"Mousavian","year":"2017"},{"key":"10.1016\/j.imavis.2026.106048_b44","doi-asserted-by":"crossref","DOI":"10.1177\/0278364913491297","article-title":"Vision meets robotics: The KITTI dataset","author":"Geiger","year":"2013","journal-title":"Int. J. Robot. Res. (IJRR)"},{"key":"10.1016\/j.imavis.2026.106048_b45","series-title":"nuScenes: A multimodal dataset for autonomous driving","author":"Caesar","year":"2020"},{"key":"10.1016\/j.imavis.2026.106048_b46","series-title":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"10386","article-title":"CLOCs: Camera-lidar object candidates fusion for 3D object detection","author":"Pang","year":"2020"},{"issue":"7","key":"10.1016\/j.imavis.2026.106048_b47","first-page":"8324","article-title":"EPNet++: Cascade bi-directional fusion for multi-modal 3D object detection","volume":"45","author":"Liu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106048_b48","series-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21653","article-title":"Virtual sparse convolution for multimodal 3D object detection","author":"Wu","year":"2023"}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001551?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001551?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T04:01:34Z","timestamp":1783051294000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626001551"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":48,"alternative-id":["S0262885626001551"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106048","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Occlusion-aware multi-modal 3D object detection via multi-stage cross-modal fusion","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106048","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"}],"article-number":"106048"}}