{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:23:55Z","timestamp":1772119435931,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"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 Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62201482"],"award-info":[{"award-number":["62201482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62201482"],"award-info":[{"award-number":["62201482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62201482"],"award-info":[{"award-number":["62201482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62201482"],"award-info":[{"award-number":["62201482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"the Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62201482"],"award-info":[{"award-number":["62201482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1007\/s00530-025-01844-z","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T08:00:54Z","timestamp":1747900854000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["PillarBAPI: enhancing pillar-based 3D object detection through attentive pseudo-image feature extraction"],"prefix":"10.1007","volume":"31","author":[{"given":"Jie","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yue","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Jietao","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Tang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,22]]},"reference":[{"key":"1844_CR1","doi-asserted-by":"crossref","unstructured":"Zhao, C., Peng, B., Azumi, T.: Point cloud automatic annotation framework for autonomous driving. In: 2024 IEEE Intelligent Vehicles Symposium (IV), pp. 3063\u20133070. IEEE (2024)","DOI":"10.1109\/IV55156.2024.10588577"},{"key":"1844_CR2","doi-asserted-by":"crossref","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: Rtm3d: Real-time monocular 3d detection from object keypoints for autonomous driving. In: European Conference on Computer Vision, pp. 644\u2013660. Springer (2020)","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"1844_CR3","volume-title":"A lidar mapping system for robot navigation in dynamic environments","author":"Z Zhou","year":"2023","unstructured":"Zhou, Z., Feng, X., Di, S., Zhou, X.: A lidar mapping system for robot navigation in dynamic environments. IEEE Trans. Intell, Vehicles (2023)"},{"key":"1844_CR4","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)"},{"issue":"1","key":"1844_CR5","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s40494-022-00844-w","volume":"11","author":"B Haznedar","year":"2023","unstructured":"Haznedar, B., Bayraktar, R., Ozturk, A.E., Arayici, Y.: Implementing pointnet for point cloud segmentation in the heritage context. Heritage Sci. 11(1), 2 (2023)","journal-title":"Heritage Sci."},{"key":"1844_CR6","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":"1844_CR7","doi-asserted-by":"crossref","unstructured":"Milioto, A., Vizzo, I., Behley, J., Stachniss, C.: Rangenet++: Fast and accurate lidar semantic segmentation. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4213\u20134220 (2019). IEEE","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"1844_CR8","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":"1844_CR9","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":"1844_CR10","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":"1844_CR11","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, B.M., Lee, G.H.: So-net: Self-organizing network for point cloud analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9397\u20139406 (2018)","DOI":"10.1109\/CVPR.2018.00979"},{"key":"1844_CR12","volume-title":"Da-net: Density-aware 3d object detection network for point clouds","author":"S Wang","year":"2023","unstructured":"Wang, S., Lu, K., Xue, J., Zhao, Y.: Da-net: Density-aware 3d object detection network for point clouds. IEEE Trans, Multimed (2023)"},{"issue":"6","key":"1844_CR13","doi-asserted-by":"publisher","first-page":"146","DOI":"10.3390\/wevj14060146","volume":"14","author":"H Xu","year":"2023","unstructured":"Xu, H., Dong, X., Wu, W., Yu, B., Zhu, H.: A two-stage pillar feature-encoding network for pillar-based 3d object detection. World Elect. Vehicle J. 14(6), 146 (2023)","journal-title":"World Elect. Vehicle J."},{"key":"1844_CR14","doi-asserted-by":"crossref","unstructured":"Xinzhe, L., Wenju, L., Liu, C., Liuqin, H.: Pillartsae: A high-performance pillar-based 3d object detection network in lidar point clouds. In: 2023 8th International Conference on Intelligent Informatics and Biomedical Sciences (ICIIBMS), vol. 8, pp. 559\u2013564 (2023). IEEE","DOI":"10.1109\/ICIIBMS60103.2023.10347716"},{"key":"1844_CR15","doi-asserted-by":"crossref","unstructured":"Cao, Z., Wang, T., Sun, P., Cao, F., Shao, S., Wang, S.: Scorepillar: A real-time small object detection method based on pillar scoring of lidar measurement. IEEE Transactions on Instrumentation and Measurement (2024)","DOI":"10.1109\/TIM.2024.3378251"},{"key":"1844_CR16","doi-asserted-by":"crossref","unstructured":"Park, K., Kim, Y., Koh, J., Park, B., Choi, J.W.: Fine-grained pillar feature encoding via spatio-temporal virtual grid for 3d object detection. arXiv:2403.06433 (2024)","DOI":"10.1109\/ICRA57147.2024.10611414"},{"key":"1844_CR17","doi-asserted-by":"crossref","unstructured":"Zhou, S., Yuan, Z., Yang, D., Wen, X., Hu, X., Shi, Y., Zhao, Z., Lu, X.: Pillarhist: A quantization-aware pillar feature encoder based on height-aware histogram. arXiv preprint arXiv:2405.18734 (2024)","DOI":"10.1109\/CVPR52734.2025.02546"},{"key":"1844_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102417","volume":"108","author":"M Hassanin","year":"2024","unstructured":"Hassanin, M., Anwar, S., Radwan, I., Khan, F.S., Mian, A.: Visual attention methods in deep learning: An in-depth survey. Inf. Fusion 108, 102417 (2024)","journal-title":"Inf. Fusion"},{"key":"1844_CR19","doi-asserted-by":"publisher","first-page":"1400","DOI":"10.7717\/peerj-cs.1400","volume":"9","author":"S Lu","year":"2023","unstructured":"Lu, S., Liu, M., Yin, L., Yin, Z., Liu, X., Zheng, W.: The multi-modal fusion in visual question answering: a review of attention mechanisms. PeerJ Computer Science 9, 1400 (2023)","journal-title":"PeerJ Computer Science"},{"issue":"3","key":"1844_CR20","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s41095-022-0271-y","volume":"8","author":"M-H Guo","year":"2022","unstructured":"Guo, M.-H., Xu, T.-X., Liu, J.-J., Liu, Z.-N., Jiang, P.-T., Mu, T.-J., Zhang, S.-H., Martin, R.R., Cheng, M.-M., Hu, S.-M.: Attention mechanisms in computer vision: A survey. Comput. Visual Media 8(3), 331\u2013368 (2022)","journal-title":"Comput. Visual Media"},{"key":"1844_CR21","doi-asserted-by":"crossref","unstructured":"Qiu, S., Wu, Y., Anwar, S., Li, C.: Investigating attention mechanism in 3d point cloud object detection. In: 2021 International Conference on 3D Vision (3DV), pp. 403\u2013412. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00050"},{"issue":"1","key":"1844_CR22","first-page":"5603123","volume":"2023","author":"X Li","year":"2023","unstructured":"Li, X., Liang, B., Huang, J., Peng, Y., Yan, Y., Li, J., Shang, W., Wei, W.: Pillar-based 3d object detection from point cloud with multiattention mechanism. Wirel. Commun. Mobile Comput. 2023(1), 5603123 (2023)","journal-title":"Wirel. Commun. Mobile Comput."},{"key":"1844_CR23","unstructured":"Thrun, S., Saul, L., Sch\u00f6lkopf, B.: Advances in neural information processing systems 16. In: Proceedings of the 2003 Conference. Illustrated Edition. London, England: The MIT Press, pp. 47\u2013110 (2004)"},{"key":"1844_CR24","doi-asserted-by":"crossref","unstructured":"Pan, X., Ge, C., Lu, R., Song, S., Chen, G., Huang, Z., Huang, G.: On the integration of self-attention and convolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 815\u2013825 (2022)","DOI":"10.1109\/CVPR52688.2022.00089"},{"issue":"9","key":"1844_CR25","doi-asserted-by":"publisher","first-page":"3877","DOI":"10.3390\/app14093877","volume":"14","author":"X Zhai","year":"2024","unstructured":"Zhai, X., Gao, Y., Chen, S., Yang, J.: Adaptive scale and correlative attention pointpillars: An efficient real-time 3d point cloud object detection algorithm. Appl. Sci. 14(9), 3877 (2024)","journal-title":"Appl. Sci."},{"key":"1844_CR26","doi-asserted-by":"crossref","unstructured":"Bhattacharyya, P., Huang, C., Czarnecki, K.: Sa-det3d: Self-attention based context-aware 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3022\u20133031 (2021)","DOI":"10.1109\/ICCVW54120.2021.00337"},{"key":"1844_CR27","unstructured":"Elharrouss, O., Akbari, Y., Almaadeed, N., Al-Maadeed, S.: Backbones-review: Feature extraction networks for deep learning and deep reinforcement learning approaches. arXiv:2206.08016 (2022)"},{"key":"1844_CR28","unstructured":"Targ, S., Almeida, D., Lyman, K.: Resnet in resnet: Generalizing residual architectures. arXiv:1603.08029 (2016)"},{"key":"1844_CR29","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1844_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, D., Hou, Q., Chen, Y., Feng, J., Yan, S.: Rethinking bottleneck structure for efficient mobile network design. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part III 16, pp. 680\u2013697 (2020). Springer","DOI":"10.1007\/978-3-030-58580-8_40"},{"key":"1844_CR31","doi-asserted-by":"crossref","unstructured":"Cai, Z., Fan, Q., Feris, R.S., Vasconcelos, N.: A unified multi-scale deep convolutional neural network for fast object detection. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part IV 14, pp. 354\u2013370 (2016). Springer","DOI":"10.1007\/978-3-319-46493-0_22"},{"key":"1844_CR32","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\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 21\u201337 (2016). Springer","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1844_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1844_CR34","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"key":"1844_CR35","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.-Y., Le, Q.V.: Nas-fpn: Learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7036\u20137045 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"1844_CR36","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., Le, Q.V.: Efficientdet: Scalable and efficient object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10781\u201310790 (2020)","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1844_CR37","unstructured":"Chen, L.-C.: Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587 (2017)"},{"key":"1844_CR38","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., Lu, H.: Dual attention network for scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3146\u20133154 (2019)","DOI":"10.1109\/CVPR.2019.00326"},{"key":"1844_CR39","volume-title":"Tinypillarnet: Tiny pillar-based network for 3d point cloud object detection at edge","author":"Y Li","year":"2023","unstructured":"Li, Y., Zhang, Y., Lai, R.: Tinypillarnet: Tiny pillar-based network for 3d point cloud object detection at edge. IEEE Trans. Circuits Syst, Video Technol (2023)"},{"key":"1844_CR40","doi-asserted-by":"crossref","unstructured":"Li, J., Luo, C., Yang, X.: Pillarnext: Rethinking network designs for 3d object detection in lidar point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17567\u201317576 (2023)","DOI":"10.1109\/CVPR52729.2023.01685"},{"issue":"2","key":"1844_CR41","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TPAMI.2022.3164083","volume":"45","author":"Y Li","year":"2022","unstructured":"Li, Y., Yao, T., Pan, Y., Mei, T.: Contextual transformer networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 1489\u20131500 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1844_CR42","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., Xu, C.: Ghostnet: More features from cheap operations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1580\u20131589 (2020)","DOI":"10.1109\/CVPR42600.2020.00165"},{"issue":"14","key":"1844_CR43","doi-asserted-by":"publisher","first-page":"3161","DOI":"10.3390\/electronics12143161","volume":"12","author":"J Wang","year":"2023","unstructured":"Wang, J., Zhang, X., Yan, T., Tan, A.: Dpnet: Dual-pyramid semantic segmentation network based on improved deeplabv3 plus. Electronics 12(14), 3161 (2023)","journal-title":"Electronics"},{"key":"1844_CR44","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":"1844_CR45","doi-asserted-by":"crossref","unstructured":"Shi, G., Li, R., Ma, C.: Pillarnet: Real-time and high-performance pillar-based 3d object detection. In: European Conference on Computer Vision, pp. 35\u201352. Springer (2022)","DOI":"10.1007\/978-3-031-20080-9_3"},{"key":"1844_CR46","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:2302.023679, (2023)"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01844-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01844-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01844-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T09:05:14Z","timestamp":1757927114000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01844-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,22]]},"references-count":46,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,8]]}},"alternative-id":["1844"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01844-z","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5430055\/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":[[2025,5,22]]},"assertion":[{"value":"11 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All the authors declare that they have no competing financial interests or personal relationships that could influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"263"}}