{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T04:01:18Z","timestamp":1749355278733,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":37,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819665754","type":"print"},{"value":"9789819665761","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-6576-1_14","type":"book-chapter","created":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T05:39:10Z","timestamp":1749274750000},"page":"197-210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Adaptive Position Encoding-Based Transformer for\u00a0Point Cloud Analysis"],"prefix":"10.1007","author":[{"given":"Jiawei","family":"Yao","sequence":"first","affiliation":[]},{"given":"Junfeng","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Yong","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Chunyang","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,8]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Armeni, I., et al.: 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":"14_CR2","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":"14_CR3","doi-asserted-by":"publisher","first-page":"4436","DOI":"10.1109\/TIP.2021.3072214","volume":"30","author":"S Cheng","year":"2021","unstructured":"Cheng, S., Chen, X., He, X., Liu, Z., Bai, X.: PRA-Net: point relation-aware network for 3D point cloud analysis. IEEE Trans. Image Process. 30, 4436\u20134448 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Choe, J., Park, C., Rameau, F., Park, J., Kweon, I.S.: PointMixer: MLP-mixer for point cloud understanding. In: European Conference on Computer Vision, pp. 620\u2013640. Springer (2022)","DOI":"10.1007\/978-3-031-19812-0_36"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Dai, A., Nie\u00dfner, M.: 3DMV: joint 3D-multi-view prediction for 3D semantic scene segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 452\u2013468 (2018)","DOI":"10.1007\/978-3-030-01249-6_28"},{"key":"14_CR6","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. Visual Media 7, 187\u2013199 (2021)","journal-title":"Comput. Visual Media"},{"key":"14_CR7","unstructured":"Hatamizadeh, A., Yin, H., Heinrich, G., Kautz, J., Molchanov, P.: Global context vision transformers. In: International Conference on Machine Learning, pp. 12633\u201312646. PMLR (2023)"},{"key":"14_CR8","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":"14_CR9","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":"14_CR10","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International Conference on Machine Learning, pp. 448\u2013456. PMLR (2015)"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Koonce, B., Koonce, B.: EfficientNet. Convolutional neural networks with swift for Tensorflow: image recognition and dataset categorization, pp. 109\u2013123 (2021)","DOI":"10.1007\/978-1-4842-6168-2_10"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Lai, X., et al.: Stratified transformer for 3D point cloud segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8500\u20138509 (2022)","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"14_CR13","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 (2018)"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Lin, H., et al.: Meta architecture for point cloud analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17682\u201317691 (2023)","DOI":"10.1109\/CVPR52729.2023.01696"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yang, X., Tang, H., Yang, S., Han, S.: FlatFormer: flattened window attention for efficient point cloud transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1200\u20131211 (2023)","DOI":"10.1109\/CVPR52729.2023.00122"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Lu, T., Wang, L., Wu, G.: CGA-Net: category guided aggregation for point cloud semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11693\u201311702 (2021)","DOI":"10.1109\/CVPR46437.2021.01152"},{"key":"14_CR17","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)"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: Voxel transformer for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3164\u20133173 (2021)","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"14_CR19","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21814\u201321823 (2023)","DOI":"10.1109\/CVPR52729.2023.02089"},{"key":"14_CR20","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":"14_CR21","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":"14_CR22","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. Adv. Neural. Inf. Process. Syst. 34, 28119\u201328130 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR23","first-page":"23192","volume":"35","author":"G Qian","year":"2022","unstructured":"Qian, G., et al.: PointNeXt: revisiting PointNet++ with improved training and scaling strategies. Adv. Neural. Inf. Process. Syst. 35, 23192\u201323204 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR24","doi-asserted-by":"publisher","first-page":"1943","DOI":"10.1109\/TMM.2021.3074240","volume":"24","author":"S Qiu","year":"2021","unstructured":"Qiu, S., Anwar, S., Barnes, N.: Geometric back-projection network for point cloud classification. IEEE Trans. Multimedia 24, 1943\u20131955 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818\u20132826 (2016)","DOI":"10.1109\/CVPR.2016.308"},{"key":"14_CR26","unstructured":"Tan, M., Le, Q.: EfficientNetV2: smaller models and faster training. In: International Conference on Machine Learning, pp. 10096\u201310106. PMLR (2021)"},{"key":"14_CR27","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":"14_CR28","doi-asserted-by":"crossref","unstructured":"Uy, M.A., Pham, Q.H., Hua, B.S., Nguyen, T., Yeung, S.K.: Revisiting point cloud classification: a new benchmark dataset and classification model on real-world data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1588\u20131597 (2019)","DOI":"10.1109\/ICCV.2019.00167"},{"key":"14_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"issue":"5","key":"14_CR30","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":"14_CR31","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10033\u201310041 (2021)","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Wu, W., Qi, Z., Fuxin, L.: PointConv: deep convolutional networks on 3D point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9621\u20139630 (2019)","DOI":"10.1109\/CVPR.2019.00985"},{"key":"14_CR33","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":"6","key":"14_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2980179.2980238","volume":"35","author":"L Yi","year":"2016","unstructured":"Yi, L., et al.: A scalable active framework for region annotation in 3D shape collections. ACM Trans. Graph. (ToG) 35(6), 1\u201312 (2016)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, R., Wang, L., Wang, Y., Gao, P., Li, H., Shi, J.: Starting from non-parametric networks for 3D point cloud analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5344\u20135353 (2023)","DOI":"10.1109\/CVPR52729.2023.00517"},{"key":"14_CR36","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"},{"key":"14_CR37","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"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6576-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T05:39:23Z","timestamp":1749274763000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6576-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819665754","9789819665761"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6576-1_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"8 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}