{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T13:03:13Z","timestamp":1760101393221,"version":"3.37.3"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T00:00:00Z","timestamp":1667001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T00:00:00Z","timestamp":1667001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the National Key R &D Program of China","award":["2019YFE0105400"],"award-info":[{"award-number":["2019YFE0105400"]}]},{"name":"the Development Project of Ship Situational Intelligent Awareness System","award":["MC-201920-X01"],"award-info":[{"award-number":["MC-201920-X01"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1007\/s00371-022-02688-8","type":"journal-article","created":{"date-parts":[[2022,10,29]],"date-time":"2022-10-29T10:14:41Z","timestamp":1667038481000},"page":"5669-5681","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["PCTP: point cloud transformer pooling block for points set abstraction structure"],"prefix":"10.1007","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0461-3619","authenticated-orcid":false,"given":"Yunqian","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guihua","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongchao","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,29]]},"reference":[{"key":"2688_CR1","doi-asserted-by":"crossref","unstructured":"Armeni, I., Sener, O., Zamir, A.R., Jiang, H., Brilakis, I., Fischer, M., Savarese, S.: 3d semantic parsing of large-scale indoor spaces. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1534\u20131543 (2016)","DOI":"10.1109\/CVPR.2016.170"},{"key":"2688_CR2","doi-asserted-by":"crossref","unstructured":"Atzmon, M., Maron, H., Lipman, Y.: Point convolutional neural networks by extension operators. arXiv preprint arXiv:1803.10091 (2018)","DOI":"10.1145\/3197517.3201301"},{"key":"2688_CR3","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: Gcnet: non-local networks meet squeeze-excitation networks and beyond. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp.\u00a00 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"2688_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2688_CR5","doi-asserted-by":"publisher","unstructured":"Chen, L., Zhang, Q.: Ddgcn: graph convolution network based on direction and distance for point cloud learning. Vis. Comput. (2022). https:\/\/doi.org\/10.1007\/s00371-021-02351-8","DOI":"10.1007\/s00371-021-02351-8"},{"key":"2688_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"2688_CR7","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"2688_CR8","doi-asserted-by":"crossref","unstructured":"Du, L., Ye, X., Tan, X., Feng, J., Xu, Z., Ding, E., Wen, S.: Associate-3ddet: perceptual-to-conceptual association for 3d point cloud object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13329\u201313338 (2020)","DOI":"10.1109\/CVPR42600.2020.01334"},{"key":"2688_CR9","doi-asserted-by":"publisher","first-page":"134826","DOI":"10.1109\/ACCESS.2021.3116304","volume":"9","author":"N Engel","year":"2021","unstructured":"Engel, N., Belagiannis, V., Dietmayer, K.: Point transformer. IEEE Access 9, 134826\u2013134840 (2021)","journal-title":"IEEE Access"},{"key":"2688_CR10","doi-asserted-by":"crossref","unstructured":"Fan, H., Yang, Y., Kankanhalli, M.: Point 4d transformer networks for spatio-temporal modeling in point cloud videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14204\u201314213 (2021)","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"2688_CR11","doi-asserted-by":"publisher","unstructured":"Fan, H., Yang, Y., Kankanhalli, M.: Point spatio-temporal transformer networks for point cloud video modeling. IEEE Trans. Pattern Anal. Mach. Intell. (2022). https:\/\/doi.org\/10.1109\/TPAMI.2022.3161735","DOI":"10.1109\/TPAMI.2022.3161735"},{"key":"2688_CR12","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"},{"issue":"2","key":"2688_CR13","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","volume":"7","author":"MH 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. Vis. Media 7(2), 187\u2013199 (2021)","journal-title":"Comput. Vis. Media"},{"key":"2688_CR14","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":"2688_CR15","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.neucom.2021.06.046","volume":"459","author":"Y He","year":"2021","unstructured":"He, Y., Xia, G., Luo, Y., Su, L., Zhang, Z., Li, W., Wang, P.: Dvfenet: dual-branch voxel feature extraction network for 3d object detection. Neurocomputing 459, 201\u2013211 (2021)","journal-title":"Neurocomputing"},{"key":"2688_CR16","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2688_CR17","doi-asserted-by":"crossref","unstructured":"Hu, Q., Yang, B., Xie, L., Rosa, S., Guo, Y., Wang, Z., Trigoni, N., Markham, A.: Randla-net: efficient semantic segmentation of large-scale point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11108\u201311117 (2020)","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"2688_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Q., Wang, W., Neumann, U.: Recurrent slice networks for 3d segmentation of point clouds. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2626\u20132635 (2018)","DOI":"10.1109\/CVPR.2018.00278"},{"key":"2688_CR19","doi-asserted-by":"crossref","unstructured":"Komarichev, A., Zhong, Z., Hua, J.: A-cnn: Annularly convolutional neural networks on point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7421\u20137430 (2019)","DOI":"10.1109\/CVPR.2019.00760"},{"key":"2688_CR20","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3d proposal generation and object detection from view aggregation. In: 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.\u00a01\u20138. IEEE (2018)","DOI":"10.1109\/IROS.2018.8594049"},{"issue":"3","key":"2688_CR21","doi-asserted-by":"publisher","first-page":"704","DOI":"10.3390\/s20030704","volume":"20","author":"H Kuang","year":"2020","unstructured":"Kuang, H., Wang, B., An, J., Zhang, M., Zhang, Z.: Voxel-fpn: multi-scale voxel feature aggregation for 3d object detection from lidar point clouds. Sensors 20(3), 704 (2020)","journal-title":"Sensors"},{"key":"2688_CR22","doi-asserted-by":"crossref","unstructured":"Landrieu, L., Simonovsky, M.: Large-scale point cloud semantic segmentation with superpoint graphs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4558\u20134567 (2018)","DOI":"10.1109\/CVPR.2018.00479"},{"key":"2688_CR23","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":"2688_CR24","first-page":"820","volume":"31","author":"Y Li","year":"2018","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: convolution on x-transformed points. Adv. Neural Inf. Process. Syst. 31, 820\u2013830 (2018)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2688_CR25","doi-asserted-by":"publisher","unstructured":"Liu, Q., Zhao, J., Cheng, C. et al.: PointALCR: adversarial latent GAN and contrastive regularization for point cloud completion. Vis Comput 38, 3341\u20133349 (2022). https:\/\/doi.org\/10.1007\/s00371-022-02550-x","DOI":"10.1007\/s00371-022-02550-x"},{"issue":"7","key":"2688_CR26","doi-asserted-by":"publisher","first-page":"2303","DOI":"10.1007\/s00371-021-02112-7","volume":"38","author":"T Liu","year":"2022","unstructured":"Liu, T., Cai, Y., Zheng, J., Thalmann, N.M.: Beacon: a boundary embedded attentional convolution network for point cloud instance segmentation. Vis. Comput. 38(7), 2303\u20132313 (2022)","journal-title":"Vis. Comput."},{"key":"2688_CR27","doi-asserted-by":"crossref","unstructured":"Liu, X., Han, Z., Liu, Y.S., Zwicker, M.: Point2sequence: learning the shape representation of 3d point clouds with an attention-based sequence to sequence network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a033, pp. 8778\u20138785 (2019)","DOI":"10.1609\/aaai.v33i01.33018778"},{"key":"2688_CR28","doi-asserted-by":"crossref","unstructured":"Liu, Y., Fan, B., Xiang, S., Pan, C.: Relation-shape convolutional neural network for point cloud analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8895\u20138904 (2019)","DOI":"10.1109\/CVPR.2019.00910"},{"key":"2688_CR29","unstructured":"Liu, Z., Tang, H., Lin, Y., Han, S.: Point-voxel CNN for efficient 3d deep learning. arXiv preprint arXiv:1907.03739 (2019)"},{"key":"2688_CR30","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":"2688_CR31","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":"2688_CR32","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. arXiv preprint arXiv:1706.02413 (2017)"},{"key":"2688_CR33","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"},{"key":"2688_CR34","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":"2688_CR35","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: Kpconv: Flexible and deformable convolution for point clouds. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6411\u20136420 (2019)","DOI":"10.1109\/ICCV.2019.00651"},{"key":"2688_CR36","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"2688_CR37","doi-asserted-by":"crossref","unstructured":"Wang, W., Yu, R., Huang, Q., Neumann, U.: Sgpn: similarity group proposal network for 3d point cloud instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2569\u20132578 (2018)","DOI":"10.1109\/CVPR.2018.00272"},{"key":"2688_CR38","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"issue":"5","key":"2688_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. (TOG) 38(5), 1\u201312 (2019)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2688_CR40","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3d shapenets: a deep representation for volumetric shapes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1912\u20131920 (2015)"},{"key":"2688_CR41","doi-asserted-by":"crossref","unstructured":"Xu, Q., Sun, X., Wu, C.Y., Wang, P., Neumann, U.: Grid-GCN for fast and scalable point cloud learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5661\u20135670 (2020)","DOI":"10.1109\/CVPR42600.2020.00570"},{"key":"2688_CR42","doi-asserted-by":"crossref","unstructured":"Yan, X., Zheng, C., Li, Z., Wang, S., Cui, S.: Pointasnl: robust point clouds processing using nonlocal neural networks with adaptive sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5589\u20135598 (2020)","DOI":"10.1109\/CVPR42600.2020.00563"},{"issue":"10","key":"2688_CR43","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":"2688_CR44","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3dssd: point-based 3d single stage object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11040\u201311048 (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"2688_CR45","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: Ipod: intensive point-based object detector for point cloud. arXiv preprint arXiv:1812.05276 (2018)","DOI":"10.1109\/ICCV.2019.00204"},{"key":"2688_CR46","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":"2688_CR47","doi-asserted-by":"crossref","unstructured":"Ye, M., Xu, S., Cao, T.: Hvnet: hybrid voxel network for lidar based 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1631\u20131640 (2020)","DOI":"10.1109\/CVPR42600.2020.00170"},{"key":"2688_CR48","doi-asserted-by":"crossref","unstructured":"Yi, H., Shi, S., Ding, M., Sun, J., Xu, K., Zhou, H., Wang, Z., Li, S., Wang, G.: Segvoxelnet: exploring semantic context and depth-aware features for 3d vehicle detection from point cloud. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 2274\u20132280. IEEE (2020)","DOI":"10.1109\/ICRA40945.2020.9196556"},{"key":"2688_CR49","unstructured":"Zarzar, J., Giancola, S., Ghanem, B.: Pointrgcn: graph convolution networks for 3d vehicles detection refinement. arXiv preprint arXiv:1911.12236 (2019)"},{"key":"2688_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Fu, C.W., Jia, J.: Pointweb: Enhancing local neighborhood features for point cloud processing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5565\u20135573 (2019)","DOI":"10.1109\/CVPR.2019.00571"},{"key":"2688_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P., Koltun, V.: Point transformer. arXiv preprint arXiv:2012.09164 (2020)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"2688_CR52","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":"2688_CR53","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02688-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-022-02688-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-022-02688-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T15:10:14Z","timestamp":1698419414000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-022-02688-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,29]]},"references-count":53,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["2688"],"URL":"https:\/\/doi.org\/10.1007\/s00371-022-02688-8","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"type":"print","value":"0178-2789"},{"type":"electronic","value":"1432-2315"}],"subject":[],"published":{"date-parts":[[2022,10,29]]},"assertion":[{"value":"22 September 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2022","order":2,"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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}