{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T17:08:43Z","timestamp":1774026523005,"version":"3.50.1"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031783944","type":"print"},{"value":"9783031783951","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78395-1_17","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T09:35:44Z","timestamp":1733132144000},"page":"249-267","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Rethinking Attention Module Design for Point Cloud Analysis"],"prefix":"10.1007","author":[{"given":"Chengzhi","family":"Wu","sequence":"first","affiliation":[]},{"given":"Kaige","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Zeyun","family":"Zhong","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Fu","sequence":"additional","affiliation":[]},{"given":"Junwei","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Jiaming","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Julius","family":"Pfrommer","sequence":"additional","affiliation":[]},{"given":"J\u00fcrgen","family":"Beyerer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"17_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"17_CR2","unstructured":"Ding, Z., Hou, J., Tu, Z.: Point cloud recognition with position-to-structure attention transformers. arXiv preprint arXiv:2210.02030 (2022)"},{"key":"17_CR3","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":"17_CR4","unstructured":"Goyal, A., Law, H., Liu, B., Newell, A., Deng, J.: Revisiting point cloud shape classification with a simple and effective baseline. In: ICML. pp. 3809\u20133820 (2021)"},{"key":"17_CR5","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. Computational Visual Media 7, 187\u2013199 (2021)","journal-title":"Computational Visual Media"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Hamdi, A., Giancola, S., Ghanem, B.: MVTN: Multi-view transformation network for 3d shape recognition. In: ICCV. pp. 1\u201311 (2021)","DOI":"10.1109\/ICCV48922.2021.00007"},{"key":"17_CR7","doi-asserted-by":"crossref","unstructured":"Han, X.F., Jin, Y.F., Cheng, H.X., Xiao, G.Q.: Dual transformer for point cloud analysis. IEEE Transactions on Multimedia (2022)","DOI":"10.1109\/TMM.2022.3198318"},{"key":"17_CR8","doi-asserted-by":"crossref","unstructured":"Hou, Z., Yan, Y., Xu, C., Kong, H.: HiTPR: Hierarchical transformer for place recognition in point cloud. In: ICRA. pp. 2612\u20132618. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811737"},{"key":"17_CR9","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: CVPR. pp. 11108\u201311117 (2020)","DOI":"10.1109\/CVPR42600.2020.01112"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Q., Dong, X., Chen, D., Zhou, H., Zhang, W., Zhang, K., Hua, G., Cheng, Y., Yu, N.: PointCAT: Contrastive adversarial training for robust point cloud recognition. IEEE Transactions on Image Processing (2024)","DOI":"10.1109\/TIP.2024.3372456"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Z., Liang, D., Xu, P., Xiang, B.: Improve transformer models with better relative position embeddings. arXiv preprint arXiv:2009.13658 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.298"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhao, Z., Li, B., Han, J.: LCPFormer: Towards effective 3d point cloud analysis via local context propagation in transformers. IEEE Transactions on Circuits and Systems for Video Technology (2023)","DOI":"10.1109\/TCSVT.2023.3247506"},{"key":"17_CR13","doi-asserted-by":"crossref","unstructured":"Hui, L., Yang, H., Cheng, M., Xie, J., Yang, J.: Pyramid point cloud transformer for large-scale place recognition. In: ICCV. pp. 6098\u20136107 (2021)","DOI":"10.1109\/ICCV48922.2021.00604"},{"key":"17_CR14","doi-asserted-by":"crossref","unstructured":"Lai, X., Liu, J., Jiang, L., Wang, L., Zhao, H., Liu, S., Qi, X., Jia, J.: Stratified transformer for 3d point cloud segmentation. In: CVPR. pp. 8500\u20138509 (2022)","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"17_CR15","doi-asserted-by":"crossref","unstructured":"Li, G., Muller, M., Thabet, A., Ghanem, B.: DeepGCNs: Can GCNs go as deep as CNNs? In: ICCV. pp. 9267\u20139276 (2019)","DOI":"10.1109\/ICCV.2019.00936"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Li, S., Gao, P., Tan, X., Wei, M.: ProxyFormer: Proxy alignment assisted point cloud completion with missing part sensitive transformer. In: CVPR. pp. 9466\u20139475 (2023)","DOI":"10.1109\/CVPR52729.2023.00913"},{"key":"17_CR17","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: Convolution on x-transformed points. NeurIPS 31 (2018)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Lin, H., Zheng, X., Li, L., Chao, F., Wang, S., Wang, Y., Tian, Y., Ji, R.: Meta architecture for point cloud analysis. In: CVPR. pp. 17682\u201317691 (2023)","DOI":"10.1109\/CVPR52729.2023.01696"},{"key":"17_CR19","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: AAAI. vol.\u00a033, pp. 8778\u20138785 (2019)","DOI":"10.1609\/aaai.v33i01.33018778"},{"key":"17_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, H., Cao, Y., Zhang, Z., Tong, X.: A closer look at local aggregation operators in point cloud analysis. In: ECCV. pp. 326\u2013342 (2020)","DOI":"10.1007\/978-3-030-58592-1_20"},{"issue":"12","key":"17_CR21","doi-asserted-by":"publisher","first-page":"24854","DOI":"10.1109\/TITS.2022.3198836","volume":"23","author":"D Lu","year":"2022","unstructured":"Lu, D., Xie, Q., Gao, K., Xu, L., Li, J.: 3DCTN: 3d convolution-transformer network for point cloud classification. IEEE Trans. Intell. Transp. Syst. 23(12), 24854\u201324865 (2022)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"17_CR22","doi-asserted-by":"crossref","unstructured":"Luong, M.T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015)","DOI":"10.18653\/v1\/D15-1166"},{"key":"17_CR23","unstructured":"Ma, X., Qin, C., You, H., Ran, H., Fu, Y.: Rethinking network design and local geometry in point cloud: A simple residual mlp framework. arXiv preprint arXiv:2202.07123 (2022)"},{"issue":"6","key":"17_CR24","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1109\/JAS.2020.1003324","volume":"8","author":"A Muzahid","year":"2020","unstructured":"Muzahid, A., Wan, W., Sohel, F., Wu, L., Hou, L.: CurveNet: Curvature-based multitask learning deep networks for 3d object recognition. IEEE\/CAA Journal of Automatica Sinica 8(6), 1177\u20131187 (2020)","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, S., Kim, S., Xiong, Y., Kim, H.J.: Self-positioning point-based transformer for point cloud understanding. In: CVPR. pp. 21814\u201321823 (2023)","DOI":"10.1109\/CVPR52729.2023.02089"},{"key":"17_CR26","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: Deep learning on point sets for 3d classification and segmentation. In: CVPR. pp. 652\u2013660 (2017)"},{"key":"17_CR27","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. NeurIPS 30 (2017)"},{"key":"17_CR28","first-page":"28119","volume":"34","author":"G Qian","year":"2021","unstructured":"Qian, G., Hammoud, H., Li, G., Thabet, A., Ghanem, B.: ASSANet: An anisotropic separable set abstraction for efficient point cloud representation learning. NeurIPS 34, 28119\u201328130 (2021)","journal-title":"NeurIPS"},{"key":"17_CR29","first-page":"23192","volume":"35","author":"G Qian","year":"2022","unstructured":"Qian, G., Li, Y., Peng, H., Mai, J., Hammoud, H., Elhoseiny, M., Ghanem, B.: PointNeXt: Revisiting pointnet++ with improved training and scaling strategies. NeurIPS 35, 23192\u201323204 (2022)","journal-title":"NeurIPS"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Qin, Z., Yu, H., Wang, C., Guo, Y., Peng, Y., Xu, K.: Geometric transformer for fast and robust point cloud registration. In: CVPR. pp. 11143\u201311152 (2022)","DOI":"10.1109\/CVPR52688.2022.01086"},{"key":"17_CR31","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. NeurIPS 32 (2019)"},{"key":"17_CR32","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: ICCV. pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Shan, J., Zhou, S., Fang, Z., Cui, Y.: PTT: Point-track-transformer module for 3d single object tracking in point clouds. In: IROS. pp. 1310\u20131316 (2021)","DOI":"10.1109\/IROS51168.2021.9636821"},{"key":"17_CR34","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"17_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: ICCV. pp. 6411\u20136420 (2019)","DOI":"10.1109\/ICCV.2019.00651"},{"key":"17_CR36","doi-asserted-by":"crossref","unstructured":"Umam, A., Yang, C.K., Chuang, Y.Y., Chuang, J.H., Lin, Y.Y.: Point mixswap: Attentional point cloud mixing via swapping matched structural divisions. In: ECCV. pp. 596\u2013611 (2022)","DOI":"10.1007\/978-3-031-19818-2_34"},{"key":"17_CR37","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. NeurIPS 30 (2017)"},{"key":"17_CR38","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., Chen, L.C.: Axial-deeplab: Stand-alone axial-attention for panoptic segmentation. In: ECCV. pp. 108\u2013126 (2020)","DOI":"10.1007\/978-3-030-58548-8_7"},{"issue":"5","key":"17_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 Transactions on Graphics 38(5), 1\u201312 (2019)","journal-title":"ACM Transactions on Graphics"},{"key":"17_CR40","doi-asserted-by":"crossref","unstructured":"Wu, C., Bi, X., Pfrommer, J., Cebulla, A., Mangold, S., Beyerer, J.: Sim2real transfer learning for point cloud segmentation: An industrial application case on autonomous disassembly. In: WACV. pp. 4531\u20134540 (2023)","DOI":"10.1109\/WACV56688.2023.00451"},{"key":"17_CR41","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.procir.2024.01.028","volume":"122","author":"C Wu","year":"2024","unstructured":"Wu, C., Fu, H., Kaiser, J.P., Barczak, E.T., Pfrommer, J., Lanza, G., Heizmann, M., Beyerer, J.: 6d pose estimation on point cloud data through prior knowledge integration: A case study in autonomous disassembly. Procedia CIRP 122, 193\u2013198 (2024)","journal-title":"Procedia CIRP"},{"key":"17_CR42","doi-asserted-by":"crossref","unstructured":"Wu, C., Huang, Q., Jin, K., Pfrommer, J., Beyerer, J.: A cross branch fusion-based contrastive learning framework for point cloud self-supervised learning. In: 3DV. pp. 528\u2013538 (2024)","DOI":"10.1109\/3DV62453.2024.00012"},{"key":"17_CR43","doi-asserted-by":"crossref","unstructured":"Wu, C., Zheng, J., Pfrommer, J., Beyerer, J.: Attention-based point cloud edge sampling. In: CVPR. pp. 5333\u20135343 (2023)","DOI":"10.1109\/CVPR52729.2023.00516"},{"key":"17_CR44","doi-asserted-by":"crossref","unstructured":"Wu, K., Peng, H., Chen, M., Fu, J., Chao, H.: Rethinking and improving relative position encoding for vision transformer. In: ICCV. pp. 10033\u201310041 (2021)","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"17_CR45","first-page":"33330","volume":"35","author":"X Wu","year":"2022","unstructured":"Wu, X., Lao, Y., Jiang, L., Liu, X., Zhao, H.: Point transformer v2: Grouped vector attention and partition-based pooling. NeurIPS 35, 33330\u201333342 (2022)","journal-title":"NeurIPS"},{"key":"17_CR46","unstructured":"Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., Xiao, J.: 3D ShapeNets: A deep representation for volumetric shapes. In: CVPR. pp. 1912\u20131920 (2015)"},{"key":"17_CR47","doi-asserted-by":"crossref","unstructured":"Xia, Y., Gladkova, M., Wang, R., Li, Q., Stilla, U., Henriques, J.F., Cremers, D.: Casspr: Cross attention single scan place recognition. In: ICCV. pp. 8461\u20138472 (2023)","DOI":"10.1109\/ICCV51070.2023.00777"},{"key":"17_CR48","doi-asserted-by":"crossref","unstructured":"Xu, C., Zhai, B., Wu, B., Li, T., Zhan, W., Vajda, P., Keutzer, K., Tomizuka, M.: You only group once: Efficient point-cloud processing with token representation and relation inference module. In: IROS. pp. 4589\u20134596. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636858"},{"issue":"6","key":"17_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2980179.2980238","volume":"35","author":"L Yi","year":"2016","unstructured":"Yi, L., Kim, V.G., Ceylan, D., Shen, I.C., Yan, M., Su, H., Lu, C., Huang, Q., Sheffer, A., Guibas, L.: A scalable active framework for region annotation in 3d shape collections. ACM Transactions on Graphics 35(6), 1\u201312 (2016)","journal-title":"ACM Transactions on Graphics"},{"key":"17_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, C., Wan, H., Shen, X., Wu, Z.: Patchformer: An efficient point transformer with patch attention. In: CVPR. pp. 11799\u201311808 (2022)","DOI":"10.1109\/CVPR52688.2022.01150"},{"key":"17_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Hua, B.S., Rosen, D.W., Yeung, S.K.: Rotation invariant convolutions for 3d point clouds deep learning. In: 3DV. pp. 204\u2013213 (2019)","DOI":"10.1109\/3DV.2019.00031"},{"key":"17_CR52","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jia, J., Koltun, V.: Exploring self-attention for image recognition. In: CVPR. pp. 10076\u201310085 (2020)","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"17_CR53","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P.H., Koltun, V.: Point transformer. In: ICCV. pp. 16259\u201316268 (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"17_CR54","doi-asserted-by":"crossref","unstructured":"Zhong, Q., Han, X.F.: Point cloud learning with transformer. arXiv preprint arXiv:2104.13636 (2021)","DOI":"10.21203\/rs.3.rs-2200447\/v1"},{"key":"17_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, C., Luo, Z., Luo, Y., Liu, T., Pan, L., Cai, Z., Zhao, H., Lu, S.: PTTR: Relational 3d point cloud object tracking with transformer. In: CVPR. pp. 8531\u20138540 (2022)","DOI":"10.1109\/CVPR52688.2022.00834"},{"key":"17_CR56","doi-asserted-by":"crossref","unstructured":"Zhou, H., Cao, Y., Chu, W., Zhu, J., Lu, T., Tai, Y., Wang, C.: SeedFormer: Patch seeds based point cloud completion with upsample transformer. In: ECCV. pp. 416\u2013432 (2022)","DOI":"10.1007\/978-3-031-20062-5_24"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78395-1_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T17:40:52Z","timestamp":1741974052000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78395-1_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031783944","9783031783951"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78395-1_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}