{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,28]],"date-time":"2026-06-28T04:55:16Z","timestamp":1782622516080,"version":"3.54.5"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Key R&D Program of Jiangsu Province","award":["BE2023010-3"],"award-info":[{"award-number":["BE2023010-3"]}]},{"name":"Jiangsu modern agricultural industry single technology research and development project","award":["CX(23)3120"],"award-info":[{"award-number":["CX(23)3120"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1007\/s00371-024-03481-5","type":"journal-article","created":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T09:00:50Z","timestamp":1717059650000},"page":"1777-1788","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["PEPillar: a point-enhanced pillar network for efficient 3D object detection in autonomous driving"],"prefix":"10.1007","volume":"41","author":[{"given":"Libo","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhu","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,30]]},"reference":[{"issue":"8","key":"3481_CR1","doi-asserted-by":"publisher","first-page":"1909","DOI":"10.1007\/s11263-023-01790-1","volume":"131","author":"J Mao","year":"2023","unstructured":"Mao, J., Shi, S., Wang, X., Li, H.: 3D object detection for autonomous driving: a comprehensive survey. Int. J. Comput. Vis. 131(8), 1909\u20131963 (2023)","journal-title":"Int. J. Comput. Vis."},{"key":"3481_CR2","unstructured":"Zhou, S., Tian, Z., Chu, X., Zhang, X., Zhang, B., Lu, X., Feng, C., Jie, Z., Chiang, P.Y., Ma, L.: Fastpillars: a deployment-friendly pillar-based 3D detector. arXiv preprint arXiv:2302.02367 (2023)"},{"key":"3481_CR3","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"3481_CR4","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"issue":"6","key":"3481_CR5","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":"3481_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"3481_CR7","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3D object detection from RGB-D data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"3481_CR8","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":"3481_CR9","doi-asserted-by":"crossref","unstructured":"Engelcke, M., Rao, D., Wang, D.Z., Tong, C.H., Posner, I.: Vote3deep: fast object detection in 3D point clouds using efficient convolutional neural networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 1355\u20131361. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989161"},{"key":"3481_CR10","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":"3481_CR11","doi-asserted-by":"crossref","unstructured":"Shi, W., Rajkumar, R.: Point-GNN: graph neural network for 3D object detection in a point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1711\u20131719 (2020)","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"3481_CR12","doi-asserted-by":"crossref","unstructured":"Pan, X., Xia, Z., Song, S., Li, L.E., Huang, G.: 3D object detection with pointformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7463\u20137472 (2021)","DOI":"10.1109\/CVPR46437.2021.00738"},{"key":"3481_CR13","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":"3481_CR14","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 5105\u20135114 (2017)"},{"key":"3481_CR15","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"},{"key":"3481_CR16","doi-asserted-by":"crossref","unstructured":"Beltr\u00e1n, J., Guindel, C., Moreno, F.M., Cruzado, D., Garcia, F., De\u00a0La\u00a0Escalera, A.: Birdnet: a 3D object detection framework from lidar information. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), pp. 3517\u20133523. IEEE (2018)","DOI":"10.1109\/ITSC.2018.8569311"},{"key":"3481_CR17","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":"3481_CR18","unstructured":"Zhou, Y., Sun, P., Zhang, Y., Anguelov, D., Gao, J., Ouyang, T., Guo, J., Ngiam, J., Vasudevan, V.: End-to-end multi-view fusion for 3D object detection in lidar point clouds. In: Conference on Robot Learning, pp. 923\u2013932. PMLR (2020)"},{"key":"3481_CR19","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"},{"key":"3481_CR20","doi-asserted-by":"crossref","unstructured":"Shi, G., Li, R., Ma, C.: Pillarnet: high-performance pillar-based 3D object detection. arXiv preprint arXiv:2205.07403 (2022)","DOI":"10.1007\/978-3-031-20080-9_3"},{"issue":"2","key":"3481_CR21","doi-asserted-by":"publisher","first-page":"1159","DOI":"10.1109\/LRA.2022.3233234","volume":"8","author":"DT Le","year":"2022","unstructured":"Le, D.T., Shi, H., Rezatofighi, H., Cai, J.: Accurate and real-time 3D pedestrian detection using an efficient attentive pillar network. IEEE Robot. Autom. Lett. 8(2), 1159\u20131166 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"3481_CR22","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1016\/j.patrec.2023.03.016","volume":"168","author":"Z Huang","year":"2023","unstructured":"Huang, Z., Zheng, Z., Zhao, J., Hu, H., Wang, Z., Chen, D.: PSA-Det3D: pillar set abstraction for 3D object detection. Pattern Recognit. Lett. 168, 138\u2013145 (2023)","journal-title":"Pattern Recognit. Lett."},{"key":"3481_CR23","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":"3481_CR24","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. Vis. 131(2), 531\u2013551 (2023)","journal-title":"Int. J. Comput. Vis."},{"key":"3481_CR25","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6000\u20136010 (2017)"},{"key":"3481_CR26","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"3481_CR27","doi-asserted-by":"crossref","unstructured":"Fan, L., Pang, Z., Zhang, T., Wang, Y.-X., Zhao, H., Wang, F., Wang, N., Zhang, Z.: Embracing single stride 3D object detector with sparse transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8458\u20138468 (2022)","DOI":"10.1109\/CVPR52688.2022.00827"},{"issue":"10","key":"3481_CR28","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":"3481_CR29","unstructured":"Graham, B., Maaten, L.: Submanifold sparse convolutional networks. arXiv preprint arXiv:1706.01307 (2017)"},{"key":"3481_CR30","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"3481_CR31","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"issue":"4","key":"3481_CR32","first-page":"5158","volume":"45","author":"Z Chen","year":"2022","unstructured":"Chen, Z., Zhong, B., Li, G., Zhang, S., Ji, R., Tang, Z., Li, X.: SiamBAN: target-aware tracking with Siamese box adaptive network. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 5158\u20135173 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3481_CR33","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"3481_CR34","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. In: Computer Vision\u2014ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3481_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Y., Fathi, A., Kundu, A., Ross, D.A., Pantofaru, C., Funkhouser, T., Solomon, J.: Pillar-based object detection for autonomous driving. In: Computer Vision\u2014ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXII 16, pp. 18\u201334. Springer (2020)","DOI":"10.1007\/978-3-030-58542-6_2"},{"key":"3481_CR36","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"3481_CR37","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3481_CR38","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","volume":"7","author":"M-H Guo","year":"2021","unstructured":"Guo, M.-H., Cai, J.-X., Liu, Z.-N., Mu, T.-J., Martin, R.R., Hu, S.-M.: PCT: point cloud transformer. Comput. Visual Media 7, 187\u2013199 (2021)","journal-title":"Comput. Visual Media"},{"key":"3481_CR39","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"issue":"9","key":"3481_CR40","doi-asserted-by":"publisher","first-page":"1305","DOI":"10.1109\/83.623193","volume":"6","author":"Y Eldar","year":"1997","unstructured":"Eldar, Y., Lindenbaum, M., Porat, M., Zeevi, Y.Y.: The farthest point strategy for progressive image sampling. IEEE Trans. Image Process. 6(9), 1305\u20131315 (1997)","journal-title":"IEEE Trans. Image Process."},{"key":"3481_CR41","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"3481_CR42","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"4","key":"3481_CR43","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.1109\/TCSVT.2022.3212987","volume":"33","author":"Y Zheng","year":"2022","unstructured":"Zheng, Y., Zhong, B., Liang, Q., Tang, Z., Ji, R., Li, X.: Leveraging local and global cues for visual tracking via parallel interaction network. IEEE Trans. Circuits Syst. Video Technol. 33(4), 1671\u20131683 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"3481_CR44","doi-asserted-by":"crossref","unstructured":"Shen, Y., Zhang, Y., Wu, Y., Wang, Z., Yang, L., Coleman, S., Kerr, D.: BSH-Det3D: improving 3D object detection with BEV shape heatmap. arXiv preprint arXiv:2303.02000 (2023)","DOI":"10.1109\/IROS55552.2023.10341930"},{"key":"3481_CR45","unstructured":"Team, O., et al.: OpenPCDet: an open-source toolbox for 3D object detection from point clouds. OD Team (2020)"},{"key":"3481_CR46","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"8","key":"3481_CR47","first-page":"2647","volume":"43","author":"S Shi","year":"2020","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3D object detection from point cloud with part-aware and part-aggregation network. IEEE Trans. Pattern Anal. Mach. Intell. 43(8), 2647\u20132664 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3481_CR48","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, vol. 35, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03481-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03481-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03481-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T14:55:33Z","timestamp":1739372133000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03481-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":48,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["3481"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03481-5","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"11 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}