{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T14:14:59Z","timestamp":1788185699330,"version":"build-2803163510"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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":["62506113"],"award-info":[{"award-number":["62506113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114481","type":"journal-article","created":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:16:14Z","timestamp":1784387774000},"page":"114481","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PE","title":["VIM-Net: A voxel-interaction multimodal network for 3D object detection"],"prefix":"10.1016","volume":"180","author":[{"given":"Minghan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7062-931X","authenticated-orcid":false,"given":"Yang","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xijiong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghuai","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ardhendu","family":"Behera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baowen","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"8","key":"10.1016\/j.patcog.2026.114481_b1","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.patcog.2026.114481_b2","series-title":"2021 IEEE International Conference on Robotics and Automation","first-page":"13656","article-title":"Penet: Towards precise and efficient image guided depth completion","author":"Hu","year":"2021"},{"key":"10.1016\/j.patcog.2026.114481_b3","doi-asserted-by":"crossref","unstructured":"Y. Liang, Y. Hu, W. Shao, Y. Fu, Distilling monocular foundation model for fine-grained depth completion, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 22254\u201322265.","DOI":"10.1109\/CVPR52734.2025.02073"},{"key":"10.1016\/j.patcog.2026.114481_b4","series-title":"Learning inverse laplacian pyramid for progressive depth completion","author":"Wang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114481_b5","doi-asserted-by":"crossref","unstructured":"X. Wu, L. Peng, H. Yang, L. Xie, C. Huang, C. Deng, H. Liu, D. Cai, Sparse fuse dense: Towards high quality 3d detection with depth completion, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5418\u20135427.","DOI":"10.1109\/CVPR52688.2022.00534"},{"key":"10.1016\/j.patcog.2026.114481_b6","doi-asserted-by":"crossref","unstructured":"H. Wu, C. Wen, S. Shi, X. Li, C. Wang, Virtual sparse convolution for multimodal 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 21653\u201321662.","DOI":"10.1109\/CVPR52729.2023.02074"},{"key":"10.1016\/j.patcog.2026.114481_b7","doi-asserted-by":"crossref","unstructured":"Y. Zhou, O. Tuzel, Voxelnet: End-to-end learning for point cloud based 3d object detection, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 4490\u20134499.","DOI":"10.1109\/CVPR.2018.00472"},{"issue":"10","key":"10.1016\/j.patcog.2026.114481_b8","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.patcog.2026.114481_b9","doi-asserted-by":"crossref","unstructured":"A.H. Lang, S. Vora, H. Caesar, L. Zhou, J. Yang, O. Beijbom, Pointpillars: Fast encoders for object detection from point clouds, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 12697\u201312705.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"10.1016\/j.patcog.2026.114481_b10","doi-asserted-by":"crossref","unstructured":"T. Yin, X. Zhou, P. Krahenbuhl, Center-based 3d object detection and tracking, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 11784\u201311793.","DOI":"10.1109\/CVPR46437.2021.01161"},{"issue":"Part B","key":"10.1016\/j.patcog.2026.114481_b11","article-title":"Dynamic clustering transformer for LiDAR-based 3D object detection","volume":"172","author":"Cui","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114481_b12","doi-asserted-by":"crossref","unstructured":"S. Shi, X. Wang, H. Li, Pointrcnn: 3d object proposal generation and detection from point cloud, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 770\u2013779.","DOI":"10.1109\/CVPR.2019.00086"},{"key":"10.1016\/j.patcog.2026.114481_b13","doi-asserted-by":"crossref","unstructured":"S. Shi, C. Guo, L. Jiang, Z. Wang, J. Shi, X. Wang, H. Li, Pv-rcnn: Point-voxel feature set abstraction for 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10529\u201310538.","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"10.1016\/j.patcog.2026.114481_b14","doi-asserted-by":"crossref","unstructured":"J. Deng, S. Shi, P. Li, W. Zhou, Y. Zhang, H. Li, Voxel r-cnn: Towards high performance voxel-based 3d object detection, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, 2021, pp. 1201\u20131209, 2.","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"10.1016\/j.patcog.2026.114481_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110254","article-title":"HRNet: 3D object detection network for point cloud with hierarchical refinement","volume":"149","author":"Lu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114481_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.trc.2024.104555","article-title":"Geometric information constraint 3D object detection from LiDAR point cloud for autonomous vehicles under adverse weather","volume":"161","author":"Qi","year":"2024","journal-title":"Transp. Res. C"},{"key":"10.1016\/j.patcog.2026.114481_b17","doi-asserted-by":"crossref","unstructured":"S. Vora, A.H. Lang, B. Helou, O. Beijbom, Pointpainting: Sequential fusion for 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 4604\u20134612.","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"10.1016\/j.patcog.2026.114481_b18","first-page":"16494","article-title":"Multimodal virtual point 3d detection","volume":"34","author":"Yin","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114481_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110284","article-title":"PVConvNet: Pixel-voxel sparse convolution for multimodal 3D object detection","volume":"149","author":"Liu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114481_b20","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.aej.2025.03.129","article-title":"SAMFNet: Scene-aware sampling and multi-stage fusion for multimodal 3D object detection","volume":"126","author":"Wang","year":"2025","journal-title":"Alex. Eng. J."},{"key":"10.1016\/j.patcog.2026.114481_b21","series-title":"2019 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.patcog.2026.114481_b22","doi-asserted-by":"crossref","unstructured":"X. Li, T. Ma, Y. Hou, B. Shi, Y. Yang, Y. Liu, X. Wu, Q. Chen, Y. Li, Y. Qiao, et al., Logonet: Towards accurate 3d object detection with local-to-global cross-modal fusion, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 17524\u201317534.","DOI":"10.1109\/CVPR52729.2023.01681"},{"key":"10.1016\/j.patcog.2026.114481_b23","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.patcog.2026.114481_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110939","article-title":"Occlusion-guided multi-modal fusion for vehicle-infrastructure cooperative 3D object detection","volume":"157","author":"Chu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114481_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112820","article-title":"Mambafusion: State-space model-driven object-scene fusion for multi-modal 3D object detection","volume":"173","author":"Ning","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114481_b26","doi-asserted-by":"crossref","unstructured":"J.S. Hu, T. Kuai, S.L. Waslander, Point density-aware voxels for lidar 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8469\u20138478.","DOI":"10.1109\/CVPR52688.2022.00828"},{"key":"10.1016\/j.patcog.2026.114481_b27","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, J. Dai, Deformable DETR: Deformable Transformers for End-to-End Object Detection, in: International Conference on Learning Representations, 2021."},{"key":"10.1016\/j.patcog.2026.114481_b28","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.patcog.2026.114481_b29","doi-asserted-by":"crossref","unstructured":"C. He, R. Li, S. Li, L. Zhang, Voxel set transformer: A set-to-set approach to 3d object detection from point clouds, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 8417\u20138427.","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"10.1016\/j.patcog.2026.114481_b30","doi-asserted-by":"crossref","unstructured":"H. Caesar, V. Bankiti, A.H. Lang, S. Vora, V.E. Liong, Q. Xu, A. Krishnan, Y. Pan, G. Baldan, O. Beijbom, nuscenes: A multimodal dataset for autonomous driving, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 11621\u201311631.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"10.1016\/j.patcog.2026.114481_b31","doi-asserted-by":"crossref","unstructured":"P. Sun, H. Kretzschmar, X. Dotiwalla, A. Chouard, V. Patnaik, P. Tsui, J. Guo, Y. Zhou, Y. Chai, B. Caine, et al., Scalability in perception for autonomous driving: Waymo open dataset, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 2446\u20132454.","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"10.1016\/j.patcog.2026.114481_b32","doi-asserted-by":"crossref","first-page":"21875","DOI":"10.52202\/079017-0688","article-title":"Depth anything v2","volume":"37","author":"Yang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114481_b33","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1016\/j.neucom.2019.10.025","article-title":"3d-ssd: Learning hierarchical features from rgb-d images for amodal 3d object detection","volume":"378","author":"Luo","year":"2020","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114481_b34","doi-asserted-by":"crossref","unstructured":"W. Zheng, W. Tang, L. Jiang, C.-W. Fu, SE-SSD: Self-ensembling single-stage object detector from point cloud, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 14494\u201314503.","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"10.1016\/j.patcog.2026.114481_b35","first-page":"1","article-title":"CasA: A cascade attention network for 3-D object detection from lidar point clouds","volume":"60","author":"Wu","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"5","key":"10.1016\/j.patcog.2026.114481_b36","doi-asserted-by":"crossref","first-page":"7126","DOI":"10.1109\/JSEN.2024.3350770","article-title":"TSSTDet: Transformation-based 3-D object detection via a spatial shape transformer","volume":"24","author":"Hoang","year":"2024","journal-title":"IEEE Sens. J."},{"key":"10.1016\/j.patcog.2026.114481_b37","doi-asserted-by":"crossref","unstructured":"C.R. Qi, W. Liu, C. Wu, H. Su, L.J. Guibas, Frustum pointnets for 3d object detection from rgb-d data, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 918\u2013927.","DOI":"10.1109\/CVPR.2018.00102"},{"key":"10.1016\/j.patcog.2026.114481_b38","series-title":"European Conference on Computer Vision","first-page":"35","article-title":"Epnet: Enhancing point features with image semantics for 3d object detection","author":"Huang","year":"2020"},{"key":"10.1016\/j.patcog.2026.114481_b39","series-title":"European Conference on Computer Vision","first-page":"720","article-title":"3d-cvf: Generating joint camera and lidar features using cross-view spatial feature fusion for 3d object detection","author":"Yoo","year":"2020"},{"key":"10.1016\/j.patcog.2026.114481_b40","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"},{"key":"10.1016\/j.patcog.2026.114481_b41","doi-asserted-by":"crossref","unstructured":"S. Pang, D. Morris, H. Radha, Fast-CLOCs: Fast camera-LiDAR object candidates fusion for 3D object detection, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 187\u2013196.","DOI":"10.1109\/WACV51458.2022.00380"},{"key":"10.1016\/j.patcog.2026.114481_b42","doi-asserted-by":"crossref","unstructured":"Z. Yu, B. Qiu, A.W. Khong, ViKIENet: Towards Efficient 3D Object Detection with Virtual Key Instance Enhanced Network, in: Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 11844\u201311853.","DOI":"10.1109\/CVPR52734.2025.01106"},{"key":"10.1016\/j.patcog.2026.114481_b43","doi-asserted-by":"crossref","unstructured":"Q. Xu, Y. Zhong, U. Neumann, Behind the curtain: Learning occluded shapes for 3d object detection, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, 2022, pp. 2893\u20132901, 3.","DOI":"10.1609\/aaai.v36i3.20194"},{"key":"10.1016\/j.patcog.2026.114481_b44","doi-asserted-by":"crossref","unstructured":"H. Wu, C. Wen, W. Li, X. Li, R. Yang, C. Wang, Transformation-equivariant 3d object detection for autonomous driving, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, 2023, pp. 2795\u20132802, 3.","DOI":"10.1609\/aaai.v37i3.25380"},{"key":"10.1016\/j.patcog.2026.114481_b45","doi-asserted-by":"crossref","unstructured":"Y. Chen, Y. Li, X. Zhang, J. Sun, J. Jia, Focal sparse convolutional networks for 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5428\u20135437.","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"10.1016\/j.patcog.2026.114481_b46","doi-asserted-by":"crossref","unstructured":"X. Pan, Z. Xia, S. Song, L.E. Li, G. Huang, 3d object detection with pointformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7463\u20137472.","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"10.1016\/j.patcog.2026.114481_b47","doi-asserted-by":"crossref","unstructured":"C. Wang, C. Ma, M. Zhu, X. Yang, Pointaugmenting: Cross-modal augmentation for 3d object detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 11794\u201311803.","DOI":"10.1109\/CVPR46437.2021.01162"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326014457?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326014457?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T13:27:00Z","timestamp":1788182820000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326014457"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":47,"alternative-id":["S0031320326014457"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114481","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"VIM-Net: A voxel-interaction multimodal network for 3D object detection","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114481","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114481"}}