{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:32:56Z","timestamp":1778081576746,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":49,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609628","type":"print"},{"value":"9789819609635","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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\/978-981-96-0963-5_2","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:47:37Z","timestamp":1733557657000},"page":"20-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["HT-SSPG:Hierarchical Transformers for\u00a0Semantic Surface Point Generation in\u00a03D Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1346-615X","authenticated-orcid":false,"given":"Wenhao","family":"Kong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4854-3736","authenticated-orcid":false,"given":"Xiaowei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, S., Shen, X., Jia, J.: Fast point r-cnn. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 9775\u20139784 (2019)","DOI":"10.1109\/ICCV.2019.00987"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Cho, H., Choi, J., Baek, G., Hwang, W.: itkd: Interchange transfer-based knowledge distillation for 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13540\u201313549 (2023)","DOI":"10.1109\/CVPR52729.2023.01301"},{"key":"2_CR3","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.\u00a035, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"issue":"12","key":"2_CR4","doi-asserted-by":"publisher","first-page":"4722","DOI":"10.1109\/TCSVT.2021.3100848","volume":"31","author":"J Deng","year":"2021","unstructured":"Deng, J., Zhou, W., Zhang, Y., Li, H.: From multi-view to hollow-3d: Hallucinated hollow-3d r-cnn for 3d object detection. IEEE Trans. Circuits Syst. Video Technol. 31(12), 4722\u20134734 (2021)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Fan, B., Zhang, K., Tian, J.: Hcpvf: Hierarchical cascaded point-voxel fusion for 3d object detection. IEEE Transactions on Circuits and Systems for Video Technology (2023)","DOI":"10.1109\/TCSVT.2023.3268849"},{"key":"2_CR6","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":"11","key":"2_CR7","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: The kitti dataset. The International Journal of Robotics Research 32(11), 1231\u20131237 (2013)","journal-title":"The International Journal of Robotics Research"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"He, C., Li, R., Li, S., Zhang, L.: Voxel set transformer: A set-to-set approach to 3d object detection from point clouds. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8417\u20138427 (2022)","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"2_CR9","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":"2_CR10","unstructured":"Hu, J.S., Kuai, T., Waslander, S.L.: Point density-aware voxels for lidar 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 8469\u20138478 (2022)"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Jie, Z., Chen, S., Chen, J., Ma, L., Jiang, Y.G.: Msmdfusion: Fusing lidar and camera at multiple scales with multi-depth seeds for 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 21643\u201321652 (2023)","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Koo, I., Lee, I., Kim, S.H., Kim, H.S., Jeon, W.j., Kim, C.: Pg-rcnn: Semantic surface point generation for 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 18142\u201318151 (2023)","DOI":"10.1109\/ICCV51070.2023.01663"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Li, J., Dong, S., Ding, L., Xu, T.: Mssvt++: Mixed-scale sparse voxel transformer with center voting for 3d object detection. IEEE transactions on pattern analysis and machine intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3345880"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Li, X., Ma, T., Hou, Y., Shi, B., Yang, Y., Liu, Y., Wu, X., Chen, Q., Li, Y., Qiao, Y., et\u00a0al.: Logonet: Towards accurate 3d object detection with local-to-global cross-modal fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17524\u201317534 (2023)","DOI":"10.1109\/CVPR52729.2023.01681"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, F., Wang, N.: Lidar r-cnn: An efficient and universal 3d object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7546\u20137555 (2021)","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"2_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108684","volume":"128","author":"Z Li","year":"2022","unstructured":"Li, Z., Yao, Y., Quan, Z., Xie, J., Yang, W.: Spatial information enhancement network for 3d object detection from point cloud. Pattern Recogn. 128, 108684 (2022)","journal-title":"Pattern Recogn."},{"key":"2_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108684","volume":"128","author":"Z Li","year":"2022","unstructured":"Li, Z., Yao, Y., Quan, Z., Yang, W., Xie, J.: Sienet: Spatial information enhancement network for 3d object detection from point cloud. Pattern Recogn. 128, 108684 (2022)","journal-title":"Pattern Recogn."},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Mao, J., Niu, M., Bai, H., Liang, X., Xu, H., Xu, C.: Pyramid r-cnn: Towards better performance and adaptability for 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2723\u20132732 (2021)","DOI":"10.1109\/ICCV48922.2021.00272"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Mao, J., Xue, Y., Niu, M., Bai, H., Feng, J., Liang, X., Xu, H., Xu, C.: 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":"2_CR20","doi-asserted-by":"crossref","unstructured":"Mao, J., Xue, Y., Niu, M., Bai, H., Feng, J., Liang, X., Xu, H., Xu, C.: 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":"2_CR21","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":"2_CR22","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":"2_CR23","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in neural information processing systems 30 (2017)"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Sheng, H., Cai, S., Liu, Y., Deng, B., Huang, J., Hua, X.S., Zhao, M.J.: Improving 3d object detection with channel-wise transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 2743\u20132752 (2021)","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"2_CR25","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":"2_CR26","unstructured":"Shi, S., Wang, Z., Wang, X., Li, H.: Part-$$\\text{a}2$$ net: 3d part-aware and aggregation neural network for object detection from point cloud. arXiv preprint arXiv:1907.036702(3) (2019)"},{"key":"2_CR27","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":"2_CR28","doi-asserted-by":"crossref","unstructured":"Shrout, O., Ben-Shabat, Y., Tal, A.: Gravos: Voxel selection for 3d point-cloud detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 21684\u201321693 (2023)","DOI":"10.1109\/CVPR52729.2023.02077"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Sun, P., Kretzschmar, H., Dotiwalla, X., Chouard, A., Patnaik, V., Tsui, P., Guo, J., Zhou, Y., Chai, Y., Caine, B., et\u00a0al.: Scalability in perception for autonomous driving: Waymo open dataset. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"2_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"2_CR31","unstructured":"Wang, Y., Deng, J., Hou, Y., Li, Y., Zhang, Y., Ji, J., Ouyang, W., Zhang, Y.: Club: Cluster meets bev for lidar-based 3d object detection. In: Oh, A., Naumann, T., Globerson, A., Saenko, K., Hardt, M., Levine, S. (eds.) Advances in Neural Information Processing Systems. vol.\u00a036, pp. 40438\u201340449. Curran Associates, Inc. (2023)"},{"key":"2_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2022.3228927","volume":"60","author":"H Wu","year":"2022","unstructured":"Wu, H., Deng, J., Wen, C., Li, X., Wang, C., Li, J.: Casa: A cascade attention network for 3-d object detection from lidar point clouds. IEEE Trans. Geosci. Remote Sens. 60, 1\u201311 (2022)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Xiao, W., Peng, Y., Liu, C., Gao, J., Wu, Y., Li, X.: Balanced sample assignment and objective for single-model multi-class 3d object detection. IEEE Transactions on Circuits and Systems for Video Technology (2023)","DOI":"10.1109\/TCSVT.2023.3248656"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Xu, Q., Zhong, Y., Neumann, U.: Behind the curtain: Learning occluded shapes for 3d object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a036, pp. 2893\u20132901 (2022)","DOI":"10.1609\/aaai.v36i3.20194"},{"issue":"10","key":"2_CR35","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":"2_CR36","doi-asserted-by":"crossref","unstructured":"Yang, H., Wang, W., Chen, M., Lin, B., He, T., Chen, H., He, X., Ouyang, W.: Pvt-ssd: Single-stage 3d object detector with point-voxel transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13476\u201313487 (2023)","DOI":"10.1109\/CVPR52729.2023.01295"},{"key":"2_CR37","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":"2_CR38","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":"2_CR39","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":"2_CR40","first-page":"16494","volume":"34","author":"T Yin","year":"2021","unstructured":"Yin, T., Zhou, X., Kr\u00e4henb\u00fchl, P.: Multimodal virtual point 3d detection. Adv. Neural. Inf. Process. Syst. 34, 16494\u201316507 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Yu, C., Peng, B., Huang, Q., Lei, J.: Pipc-3ddet: Harnessing perspective information and proposal correlation for 3d point cloud object detection. IEEE Transactions on Circuits and Systems for Video Technology (2023)","DOI":"10.1109\/TCSVT.2023.3296583"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Yuan, W., Khot, T., Held, D., Mertz, C., Hebert, M.: Pcn: Point completion network. In: 2018 international conference on 3D vision (3DV). pp. 728\u2013737. IEEE (2018)","DOI":"10.1109\/3DV.2018.00088"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hu, Q., Xu, G., Ma, Y., Wan, J., Guo, Y.: Not all points are equal: Learning highly efficient point-based detectors for 3d lidar point clouds. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 18953\u201318962 (2022)","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Zhao, T., Ning, X., Hong, K., Qiu, Z., Lu, P., Zhao, Y., Zhang, L., Zhou, L., Dai, G., Yang, H., et\u00a0al.: Ada3d: Exploiting the spatial redundancy with adaptive inference for efficient 3d object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 17728\u201317738 (2023)","DOI":"10.1109\/ICCV51070.2023.01625"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Zhi, P., Zhou, K., Li, Y., Wang, S.: Feature decoupling and uncertainty estimation for 3d object detection. In: 2023 IEEE International Conference on Multimedia and Expo (ICME). pp. 1133\u20131138. IEEE (2023)","DOI":"10.1109\/ICME55011.2023.00198"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, C., Zhang, Y., Chen, J., Huang, D.: Octr: Octree-based transformer for 3d object detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. pp. 5166\u20135175 (2023)","DOI":"10.1109\/CVPR52729.2023.00500"},{"issue":"11","key":"2_CR47","doi-asserted-by":"publisher","first-page":"2605","DOI":"10.3390\/rs14112605","volume":"14","author":"Q Zhou","year":"2022","unstructured":"Zhou, Q., Yu, C.: Point rcnn: An angle-free framework for rotated object detection. Remote Sensing 14(11), 2605 (2022)","journal-title":"Remote Sensing"},{"key":"2_CR48","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":"2_CR49","doi-asserted-by":"crossref","unstructured":"Zhu, B., Wang, Z., Shi, S., Xu, H., Hong, L., Li, H.: Conquer: Query contrast voxel-detr for 3d object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9296\u20139305 (2023)","DOI":"10.1109\/CVPR52729.2023.00897"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0963-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:37:44Z","timestamp":1733560664000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0963-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609628","9789819609635"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0963-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}