{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T12:13:48Z","timestamp":1775132028434,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62103298"],"award-info":[{"award-number":["No. 62103298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62103298"],"award-info":[{"award-number":["No. 62103298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62103298"],"award-info":[{"award-number":["No. 62103298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62103298"],"award-info":[{"award-number":["No. 62103298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62103298"],"award-info":[{"award-number":["No. 62103298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62103298"],"award-info":[{"award-number":["No. 62103298"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The South African National Research Foundation Incentive","award":["No.81705"],"award-info":[{"award-number":["No.81705"]}]},{"name":"The South African National Research Foundation Incentive","award":["No.81705"],"award-info":[{"award-number":["No.81705"]}]},{"name":"The South African National Research Foundation Incentive","award":["No.81705"],"award-info":[{"award-number":["No.81705"]}]},{"name":"The South African National Research Foundation Incentive","award":["No.81705"],"award-info":[{"award-number":["No.81705"]}]},{"name":"The South African National Research Foundation Incentive","award":["No.81705"],"award-info":[{"award-number":["No.81705"]}]},{"name":"The South African National Research Foundation Incentive","award":["No.81705"],"award-info":[{"award-number":["No.81705"]}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 6230324"],"award-info":[{"award-number":["No. 6230324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 6230324"],"award-info":[{"award-number":["No. 6230324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 6230324"],"award-info":[{"award-number":["No. 6230324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 6230324"],"award-info":[{"award-number":["No. 6230324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 6230324"],"award-info":[{"award-number":["No. 6230324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 6230324"],"award-info":[{"award-number":["No. 6230324"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Nat- ural Science Foundation of Tianjin City","award":["No. 22JCQNJC01440"],"award-info":[{"award-number":["No. 22JCQNJC01440"]}]},{"name":"the Nat- ural Science Foundation of Tianjin City","award":["No. 22JCQNJC01440"],"award-info":[{"award-number":["No. 22JCQNJC01440"]}]},{"name":"the Nat- ural Science Foundation of Tianjin City","award":["No. 22JCQNJC01440"],"award-info":[{"award-number":["No. 22JCQNJC01440"]}]},{"name":"the Nat- ural Science Foundation of Tianjin City","award":["No. 22JCQNJC01440"],"award-info":[{"award-number":["No. 22JCQNJC01440"]}]},{"name":"the Nat- ural Science Foundation of Tianjin City","award":["No. 22JCQNJC01440"],"award-info":[{"award-number":["No. 22JCQNJC01440"]}]},{"name":"the Nat- ural Science Foundation of Tianjin City","award":["No. 22JCQNJC01440"],"award-info":[{"award-number":["No. 22JCQNJC01440"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s00530-025-02169-7","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T03:42:41Z","timestamp":1770090161000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A dual roi feature fusion for 3D object detection"],"prefix":"10.1007","volume":"32","author":[{"given":"Qingao","family":"Meng","sequence":"first","affiliation":[]},{"given":"Jigang","family":"Tong","sequence":"additional","affiliation":[]},{"given":"Sen","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Tian","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Shengzhi","family":"Du","sequence":"additional","affiliation":[]},{"given":"Wenyu","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"key":"2169_CR1","doi-asserted-by":"crossref","unstructured":"Li, B., Ouyang, W., Sheng, L., Zeng, X., Wang, X.: Gs3d: an efficient 3d object detection framework for autonomous driving. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 1019\u20131028 (2019)","DOI":"10.1109\/CVPR.2019.00111"},{"issue":"1","key":"2169_CR2","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/s11036-023-02092-z","volume":"28","author":"G Xu","year":"2023","unstructured":"Xu, G., Xu, X., Gao, H., Xiao, F.: Fp-rcnn: a real-time 3d target detection model based on multiple foreground point sampling for autonomous driving. Mob. Netw. Appl. 28(1), 369\u2013381 (2023)","journal-title":"Mob. Netw. Appl."},{"key":"2169_CR3","doi-asserted-by":"crossref","unstructured":"Liu, C., Tao, Y., Liang, J., Li, K., Chen, Y.: Object detection based on yolo network. In: 2018 IEEE 4th information technology and mechatronics engineering conference (ITOEC), IEEE, pp. 799\u2013803 (2018)","DOI":"10.1109\/ITOEC.2018.8740604"},{"issue":"16","key":"2169_CR4","doi-asserted-by":"publisher","first-page":"7190","DOI":"10.3390\/s23167190","volume":"23","author":"G Wang","year":"2023","unstructured":"Wang, G., Chen, Y., An, P., Hong, H., Hu, J., Huang, T.: UAV-Yolov8: a small-object-detection model based on improved yolov8 for UAV aerial photography scenarios. Sensors 23(16), 7190 (2023)","journal-title":"Sensors"},{"key":"2169_CR5","doi-asserted-by":"crossref","unstructured":"Xiao, P., Shao, Z., Hao, S., et\u00a0al.: Pandaset: advanced sensor suite dataset for autonomous driving. In: 2021 IEEE international intelligent transportation systems conference (ITSC), IEEE, pp. 3095\u20133101 (2021)","DOI":"10.1109\/ITSC48978.2021.9565009"},{"issue":"8","key":"2169_CR6","doi-asserted-by":"publisher","first-page":"1782","DOI":"10.1364\/AO.9.001782","volume":"9","author":"R Collis","year":"1970","unstructured":"Collis, R.: Lidar. Appl. Opt. 9(8), 1782\u20131788 (1970)","journal-title":"Appl. Opt."},{"key":"2169_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3d object detection for autonomous driving. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2147\u20132156 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"2169_CR8","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, W., Urtasun, R.: Pixor: real-time 3d object detection from point clouds. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 7652\u20137660 (2018)","DOI":"10.1109\/CVPR.2018.00798"},{"key":"2169_CR9","doi-asserted-by":"crossref","unstructured":"He, C., Zeng, H., Huang, J., Hua, X.S., Zhang, L.: Structure aware single-stage 3d object detection from point cloud. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11873\u201311882 (2020)","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"2169_CR10","doi-asserted-by":"publisher","unstructured":"Xiao, K., Li, T., Li, J., Huang, D., Peng, Y.: Equal emphasis on data and network: a two-stage 3d point cloud object detection algorithm with feature alignment. Remote Sens. 16(2) (2024). https:\/\/doi.org\/10.3390\/rs16020249, https:\/\/www.mdpi.com\/2072-4292\/16\/2\/249. Accessed 21 Mar 2025","DOI":"10.3390\/rs16020249"},{"key":"2169_CR11","doi-asserted-by":"crossref","unstructured":"Sheng, H., Cai, S., Liu, Y., Deng, B., Huang, J., Hua, X.S., Zhao, M.J.: Improving 3d object detection with channel-wise transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 2743\u20132752 (2021)","DOI":"10.1109\/ICCV48922.2021.00274"},{"issue":"8","key":"2169_CR12","doi-asserted-by":"publisher","first-page":"8527","DOI":"10.1109\/TITS.2024.3392783","volume":"25","author":"CH Wang","year":"2024","unstructured":"Wang, C.H., Chen, H.W., Chen, Y., Hsiao, P.Y., Fu, L.C.: Vopifnet: voxel-pixel fusion network for multi-class 3d object detection. IEEE Trans. Intell. Transp. Syst. 25(8), 8527\u20138537 (2024)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2169_CR13","doi-asserted-by":"crossref","unstructured":"Pang, S., Morris, D., Radha, H.: Clocs: camera-lidar object candidates fusion for 3d object detection. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, pp. 10386\u201310393 (2020)","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"2169_CR14","doi-asserted-by":"crossref","unstructured":"Huang, T., Liu, Z., Chen, X., Bai, X.: Epnet: enhancing point features with image semantics for 3d object detection. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XV 16, Springer, Berlin, pp. 35\u201352 (2020)","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"2169_CR15","doi-asserted-by":"crossref","unstructured":"Yoo, J.H., Kim, Y., Kim, J., Choi, J.W.: 3d-cvf: generating joint camera and lidar features using cross-view spatial feature fusion for 3d object detection. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part XXVII 16, Springer, Berlin, pp. 720\u2013736 (2020)","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"2169_CR16","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1109\/TMM.2023.3270638","volume":"27","author":"Z Liu","year":"2023","unstructured":"Liu, Z., Cheng, J., Fan, J., Lin, S., Wang, Y., Zhao, X.: Multi-modal fusion based on depth adaptive mechanism for 3d object detection. IEEE Trans. Multimedia 27, 707\u2013717 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"2169_CR17","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 652\u2013660 (2017)"},{"key":"2169_CR18","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"2169_CR19","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"2169_CR20","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: Std: sparse-to-dense 3d object detector for point cloud. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 1951\u20131960 (2019)","DOI":"10.1109\/ICCV.2019.00204"},{"key":"2169_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.111856","volume":"162","author":"F Sun","year":"2024","unstructured":"Sun, F., Tong, G., Song, Y.: Efficient flexible voxel-based two-stage network for 3d object detection in autonomous driving. Appl. Soft Comput. 162, 111856 (2024)","journal-title":"Appl. Soft Comput."},{"key":"2169_CR22","doi-asserted-by":"crossref","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel r-cnn: towards high performance voxel-based 3d object detection. In: Proceedings of the AAAI conference on artificial intelligence, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"2169_CR23","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"issue":"10","key":"2169_CR24","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"2169_CR25","unstructured":"Hu, J.S., Kuai, T., Waslander, S.L.: Point density-aware voxels for lidar 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 8469\u20138478 (2022)"},{"key":"2169_CR26","doi-asserted-by":"publisher","first-page":"12034","DOI":"10.1109\/TITS.2024.3373227","volume":"25","author":"B Li","year":"2024","unstructured":"Li, B., Chen, J., Li, X., Xu, R., Li, Q., Cao, Y., Wu, J., Qu, L., Li, Y., Diniz, P.S.: Vfl3d: a single-stage fine-grained lightweight point cloud 3d object detection algorithm based on voxels. IEEE Trans. Intell. Transp. Syst. 25, 12034\u201312048 (2024)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2169_CR27","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fast encoders for object detection from point clouds. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"issue":"9","key":"2169_CR28","doi-asserted-by":"publisher","first-page":"15824","DOI":"10.1109\/TITS.2022.3145588","volume":"23","author":"K Peng","year":"2022","unstructured":"Peng, K., Fei, J., Yang, K., Roitberg, A., Zhang, J., Bieder, F., Heidenreich, P., Stiller, C., Stiefelhagen, R.: Mass: multi-attentional semantic segmentation of lidar data for dense top-view understanding. IEEE Trans. Intell. Transp. Syst. 23(9), 15824\u201315840 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"2169_CR29","doi-asserted-by":"crossref","unstructured":"Liu, B., Wang, M., Foroosh, H., Tappen, M., Pensky, M.: Sparse convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 806\u2013814 (2015)","DOI":"10.1109\/CVPR.2015.7298681"},{"key":"2169_CR30","doi-asserted-by":"crossref","unstructured":"Chen, Y., Li, Y., Zhang, X., Sun, J., Jia, J.: Focal sparse convolutional networks for 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5428\u20135437 (2022)","DOI":"10.1109\/CVPR52688.2022.00535"},{"key":"2169_CR31","doi-asserted-by":"crossref","unstructured":"Zhu, T., Shen, J., Wang, C., Xiong, H.: Drop sparse convolution for 3d object detection. In: ICASSP 2024\u20132024 IEEE International Conference on Acoustics, pp. 3185\u20133189. IEEE, Speech and Signal Processing (ICASSP) (2024)","DOI":"10.1109\/ICASSP48485.2024.10447150"},{"key":"2169_CR32","unstructured":"Su, Z., Tan, P.S., Wang, Y.H.: Dv-det: efficient 3d point cloud object detection with dynamic voxelization (2021). arXiv preprint arXiv:2107.12707. Accessed 21 Mar 2025"},{"issue":"6","key":"2169_CR33","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2169_CR34","volume":"132","author":"A Liang","year":"2024","unstructured":"Liang, A., Hua, H., Fang, J., Zhao, H., Liu, T.: Boosting 3d point-based object detection by reducing information loss caused by discontinuous receptive fields. Int. J. Appl. Earth Obs. Geoinf. 132, 104049 (2024)","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"2169_CR35","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2024.112117","volume":"165","author":"Q Tang","year":"2024","unstructured":"Tang, Q., Yang, M., Wang, Z., Dong, W., Liu, Y.: Boundary points guided 3d object detection for point clouds. Appl. Soft Comput. 165, 112117 (2024)","journal-title":"Appl. Soft Comput."},{"key":"2169_CR36","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, J., Zhang, X., Qi, X., Jia, J.: Voxelnext: fully sparse voxelnet for 3d object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21674\u201321683 (2023)","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"2169_CR37","doi-asserted-by":"crossref","unstructured":"Lee, J.K., Lee, J.H., Lee, J., Kwon, S., Jung, H.: Re-voxeldet: rethinking neck and head architectures for high-performance voxel-based 3d detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 7503\u20137512 (2024)","DOI":"10.1109\/WACV57701.2024.00733"},{"key":"2169_CR38","doi-asserted-by":"crossref","unstructured":"Fei, J., Peng, K., Heidenreich, P., Bieder, F., Stiller, C.: Pillarsegnet: pillar-based semantic grid map estimation using sparse lidar data. In: 2021 IEEE intelligent vehicles symposium (IV), IEEE, pp. 838\u2013844 (2021)","DOI":"10.1109\/IV48863.2021.9575694"},{"key":"2169_CR39","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., Li, H.: Pv-rcnn: point-voxel feature set abstraction for 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 10529\u201310538 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"issue":"2","key":"2169_CR40","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11263-022-01710-9","volume":"131","author":"S Shi","year":"2023","unstructured":"Shi, S., Jiang, L., Deng, J., Wang, Z., Guo, C., Shi, J., Wang, X., Li, H.: Pv-rcnn++: point-voxel feature set abstraction with local vector representation for 3d object detection. Int. J. Comput. Vision 131(2), 531\u2013551 (2023)","journal-title":"Int. J. Comput. Vision"},{"key":"2169_CR41","doi-asserted-by":"publisher","unstructured":"Leng, Z., Sun, P., He, T., Anguelov, D., Tan, M.: Pvtransformer: point-to-voxel transformer for scalable 3d object detection. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 4238\u2013424 (2024). https:\/\/doi.org\/10.1109\/ICRA57147.2024.10610346","DOI":"10.1109\/ICRA57147.2024.10610346"},{"key":"2169_CR42","doi-asserted-by":"crossref","unstructured":"Yang, H., Wang, W., Chen, M., Lin, B., He, T., Chen, H., He, X., Ouyang, W.: Pvt-ssd: single-stage 3d object detector with point-voxel transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13476\u201313487 (2023)","DOI":"10.1109\/CVPR52729.2023.01295"},{"key":"2169_CR43","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhao, X., Huang, T., Hu, R., Zhou, Y., Bai, X.: Tanet: robust 3d object detection from point clouds with triple attention. In: Proceedings of the AAAI conference on artificial intelligence, pp. 11677\u201311684 (2020)","DOI":"10.1609\/aaai.v34i07.6837"},{"key":"2169_CR44","unstructured":"Graham, B., Van\u00a0der Maaten, L.: Sub-manifold sparse convolutional networks (2017). arXiv preprint arXiv:1706.01307. Accessed 22 Mar 2025"},{"key":"2169_CR45","doi-asserted-by":"crossref","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: Bevdet: high-performance multi-camera 3d object detection in bird-eye-view (2021). arXiv preprint arXiv:2112.11790. Accessed 22 Mar 2025","DOI":"10.1016\/j.imavis.2025.105428"},{"key":"2169_CR46","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"issue":"4","key":"2169_CR47","doi-asserted-by":"publisher","first-page":"2062","DOI":"10.1109\/LRA.2023.3244124","volume":"8","author":"G Tong","year":"2023","unstructured":"Tong, G., Li, Z., Peng, H., Wang, Y.: Multi-source features fusion single stage 3d object detection with transformer. IEEE Robot. Autom. Lett. 8(4), 2062\u20132069 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"issue":"1","key":"2169_CR48","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/LRA.2023.3331290","volume":"9","author":"P Deng","year":"2023","unstructured":"Deng, P., Zhou, L., Chen, J.: Vrvp: valuable region and valuable point anchor-free 3d object detection. IEEE Robot. Autom. Lett. 9(1), 33\u201340 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"2169_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2024.115820","volume":"242","author":"J Cao","year":"2025","unstructured":"Cao, J., Peng, Y., Wei, H., Mo, L., Fan, L., Wang, L.: Kptr: key point transformer for lidar-based 3d object detection. Measurement 242, 115820 (2025)","journal-title":"Measurement"},{"issue":"11","key":"2169_CR50","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02169-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02169-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02169-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T11:36:29Z","timestamp":1775129789000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02169-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":50,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2169"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02169-7","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7170590\/v1","asserted-by":"object"}]},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]},"assertion":[{"value":"20 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"94"}}