{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,14]],"date-time":"2026-08-14T15:44:52Z","timestamp":1786722292423,"version":"build-2736575974"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T00:00:00Z","timestamp":1733875200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176012"],"award-info":[{"award-number":["62176012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1007\/s11263-024-02313-2","type":"journal-article","created":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T22:03:57Z","timestamp":1733954637000},"page":"2783-2804","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["CMAE-3D: Contrastive Masked AutoEncoders for Self-Supervised 3D Object Detection"],"prefix":"10.1007","volume":"133","author":[{"given":"Yanan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,11]]},"reference":[{"key":"2313_CR1","unstructured":"Bao, H., Dong, L., Piao, S., & Wei, F. (2022). Beit: Bert pre-training of image transformers. in International Conference on Learning Representations."},{"key":"2313_CR2","doi-asserted-by":"crossref","unstructured":"Boulch, A., Sautier, C., Michele, B., Puy, G., & Marlet, R. (2023). Also: Automotive lidar self-supervision by occupancy estimation. in |textitProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13455\u201313465.","DOI":"10.1109\/CVPR52729.2023.01293"},{"key":"2313_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., Krishnan, A., Pan, Y., Baldan, G., & Beijbom, O. (2020). nuscenes: A multimodal dataset for autonomous driving. in Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11621\u201311631.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"2313_CR4","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., & Joulin, A. (2020). Unsupervised learning of visual features by contrasting cluster assignments. Advances in Neural Information Processing Systems, 33, 9912\u20139924.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2313_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., & He, K. (2021). Exploring simple siamese representation learning. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758.","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"2313_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C., Chen, Z., Zhang, J., & Tao, D. (2022a). Sasa: Semantics-augmented set abstraction for point-based 3d object detection. in Proceedings of the AAAI Conference on Artificial Intelligence, pp. 221\u2013229.","DOI":"10.1609\/aaai.v36i1.19897"},{"key":"2313_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. in International Conference on Machine Learning, PMLR, pp. 1597\u20131607."},{"key":"2313_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, S., Shen, X., & Jia, J. (2019). Fast point r-cnn. in Proceedings of the IEEE\/CVF International conference on Computer Vision, pp. 9775\u20139784.","DOI":"10.1109\/ICCV.2019.00987"},{"key":"2313_CR9","unstructured":"Chen, R., Mu, Y., Xu, R., Shao, W., Jiang, C., Xu, H., Li, Z., & Luo, P. (2022b). $${\\rm Co}^3$$ Cooperative unsupervised 3d representation learning for autonomous driving. arXiv:2206.04028"},{"key":"2313_CR10","doi-asserted-by":"crossref","unstructured":"Du, B., Gao, X., Hu, W., & Li, X. (2021) Self-contrastive learning with hard negative sampling for self-supervised point cloud learning. in Proceedings of the 29th ACM International Conference on Multimedia, pp. 3133\u20133142.","DOI":"10.1145\/3474085.3475458"},{"key":"2313_CR11","doi-asserted-by":"crossref","unstructured":"Fan, L., Pang, Z., Zhang, T., Wang, Y. X., Zhao, H., Wang, F., Wang, N., & Zhang, Z. (2022). 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.","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"2313_CR12","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., & Urtasun, R. (2012). Are we ready for autonomous driving? the kitti vision benchmark suite. in 2012 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 1, 3354\u20133361.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2313_CR13","first-page":"21271","volume":"33","author":"JB Grill","year":"2020","unstructured":"Grill, J. B., Strub, F., Altch\u00e9, F., Tallec, C., Richemond, P., Buchatskaya, E., Doersch, C., Avila Pires, B., Guo, Z., Gheshlaghi Azar, M., et al. (2020). Bootstrap your own latent-a new approach to self-supervised learning. Advances in Neural Information Processing Systems, 33, 21271\u201321284.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2313_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., & Girshick, R. (2022b). Masked autoencoders are scalable vision learners. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 16000\u201316009.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"2313_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020b). Momentum contrast for unsupervised visual representation learning. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2313_CR16","doi-asserted-by":"crossref","unstructured":"He, C., Li, R., Li, S., & Zhang, L. (2022a). 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, 8417\u20138427.","DOI":"10.1109\/CVPR52688.2022.00823"},{"key":"2313_CR17","doi-asserted-by":"crossref","unstructured":"He, C., Zeng, H., Huang, J., Hua, X. S., & Zhang, L. (2020a). 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.","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"2313_CR18","doi-asserted-by":"crossref","unstructured":"Hess, G., Jaxing, J., Svensson, E., Hagerman, D., Petersson, C., & Svensson, L. (2023). Masked autoencoder for self-supervised pre-training on lidar point clouds. in Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 350\u2013359.","DOI":"10.1109\/WACVW58289.2023.00039"},{"key":"2313_CR19","doi-asserted-by":"crossref","unstructured":"Hou, J., Graham, B., Nie\u00dfner, M., & Xie, S. (2021). Exploring data-efficient 3d scene understanding with contrastive scene contexts. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 15587\u201315597.","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"2313_CR20","doi-asserted-by":"crossref","unstructured":"Huang, S., Xie, Y., Zhu, S. C., & Zhu, Y. (2021). Spatio-temporal self-supervised representation learning for 3d point clouds. in Proceedings of the IEEE\/CVF International Conference on Computer Vision, 6535\u20136545.","DOI":"10.1109\/ICCV48922.2021.00647"},{"key":"2313_CR21","unstructured":"Krispel, G., Schinagl, D., Fruhwirth-Reisinger, C., Possegger, H., & Bischof, H. (2022). Maeli-masked autoencoder for large-scale lidar point clouds. arXiv:2212.07207"},{"key":"2313_CR22","doi-asserted-by":"crossref","unstructured":"Lang, A. H., Vora, S., Caesar, H., Zhou, L., Yang, J., & Beijbom, O. (2019). Pointpillars: Fast encoders for object detection from point clouds. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 12697\u201312705.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"2313_CR23","doi-asserted-by":"crossref","unstructured":"Liang, H., Jiang, C., Feng, D., Chen, X., Xu, H., Liang, X., Zhang, W., Li, Z., & Van Gool, L. (2021). Exploring geometry-aware contrast and clustering harmonization for self-supervised 3d object detection. in Proceedings of the IEEE\/CVF International Conference on Computer Vision, 3293\u20133302.","DOI":"10.1109\/ICCV48922.2021.00328"},{"key":"2313_CR24","unstructured":"Lin, Z., & Wang, Y. (2022). Bev-mae: Bird\u2019s eye view masked autoencoders for outdoor point cloud pre-training. arXiv:2212.05758"},{"key":"2313_CR25","doi-asserted-by":"crossref","unstructured":"Liu, H., Cai, M., & Lee, Y. J. (2022). Masked discrimination for self-supervised learning on point clouds. in European Conference on Computer Vision, Springer, 657\u2013675.","DOI":"10.1007\/978-3-031-20086-1_38"},{"key":"2313_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.gmod.2023.101188","volume":"129","author":"Z Lu","year":"2023","unstructured":"Lu, Z., Dai, Y., Li, W., & Su, Z. (2023). Joint data and feature augmentation for self-supervised representation learning on point clouds. Graphical Models, 129, 101188.","journal-title":"Graphical Models"},{"key":"2313_CR27","unstructured":"Mao, J., Niu, M., Jiang, C., Liang, H., Chen, J., Liang, X., Li, Y., Ye, C., Zhang, W., Li, Z., et al. (2021a). One million scenes for autonomous driving: Once dataset. arXiv:2106.11037."},{"key":"2313_CR28","doi-asserted-by":"crossref","unstructured":"Mao, J., Xue, Y., Niu, M., Bai, H., Feng, J., Liang, X., Xu, H., & Xu, C. (2021b). Voxel transformer for 3d object detection. in Proceedings of the IEEE\/CVF International Conference on Computer Vision, 3164\u20133173.","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"2313_CR29","first-page":"1","volume":"1","author":"J Mao","year":"2023","unstructured":"Mao, J., Shi, S., Wang, X., & Li, H. (2023). 3d object detection for autonomous driving: A comprehensive survey. International Journal of Computer Vision, 1, 1\u201355.","journal-title":"International Journal of Computer Vision"},{"key":"2313_CR30","doi-asserted-by":"crossref","unstructured":"Min, C., Xiao, L., Zhao, D., Nie, Y., & Dai, B. (2023). Occupancy-mae: Self-supervised pre-training large-scale lidar point clouds with masked occupancy autoencoders. IEEE Transactions on Intelligent Vehicles.","DOI":"10.1109\/TIV.2023.3322409"},{"key":"2313_CR31","doi-asserted-by":"crossref","unstructured":"Noh, J., Lee, S., & Ham, B. (2021). Hvpr: Hybrid voxel-point representation for single-stage 3d object detection. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 14605\u201314614.","DOI":"10.1109\/CVPR46437.2021.01437"},{"key":"2313_CR32","doi-asserted-by":"crossref","unstructured":"Pang, Y., Wang, W., Tay, F. E., Liu, W., Tian, Y., & Yuan, L. (2022). Masked autoencoders for point cloud self-supervised learning. in European Conference on Computer Vision, Springer, 604\u2013621.","DOI":"10.1007\/978-3-031-20086-1_35"},{"key":"2313_CR33","doi-asserted-by":"crossref","unstructured":"Qi, C. R., Liu, W., Wu, C., Su, H., & Guibas, L. J. (2018). Frustum pointnets for 3d object detection from rgb-d data. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 918\u2013927.","DOI":"10.1109\/CVPR.2018.00102"},{"key":"2313_CR34","unstructured":"Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2017a). Pointnet: Deep learning on point sets for 3d classification and segmentation. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 652\u2013660."},{"key":"2313_CR35","unstructured":"Qi, C. R., Yi, L., Su, H., & Guibas, L. J. (2017b). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. Advances in Neural Information Processing Systems, 30"},{"key":"2313_CR36","unstructured":"Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28,"},{"key":"2313_CR37","doi-asserted-by":"crossref","unstructured":"Sanghi, A. (2020). Info3d: Representation learning on 3d objects using mutual information maximization and contrastive learning. in European Conference on Computer Vision, Springer 626\u2013642.","DOI":"10.1007\/978-3-030-58526-6_37"},{"key":"2313_CR38","doi-asserted-by":"crossref","unstructured":"Sautier, C., Puy, G., Boulch, A., Marlet, R., & Lepetit, V. (2023). Bevcontrast: Self-supervision in bev space for automotive lidar point clouds. arXiv:2310.17281","DOI":"10.1109\/3DV62453.2024.00017"},{"key":"2313_CR39","doi-asserted-by":"crossref","unstructured":"Shi, S., Guo, C., Jiang, L., Wang, Z., Shi, J., Wang, X., & Li, H. (2020a). 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.","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"2313_CR40","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., & Li, H. (2019). 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.","DOI":"10.1109\/CVPR.2019.00086"},{"issue":"2","key":"2313_CR41","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11263-022-01710-9","volume":"131","author":"S Shi","year":"2023","unstructured":"Shi, S., Jiang, L., Deng, J., Wang, Z., Guo, C., Shi, J., Wang, X., & Li, H. (2023). Pv-rcnn++: Point-voxel feature set abstraction with local vector representation for 3d object detection. International Journal of Computer Vision, 131(2), 531\u2013551.","journal-title":"International Journal of Computer Vision"},{"issue":"8","key":"2313_CR42","first-page":"2647","volume":"43","author":"S Shi","year":"2020","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., & Li, H. (2020b). From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(8), 2647\u20132664.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2313_CR43","unstructured":"Shrout, O., Nitzan, O., Ben-Shabat, Y., & Tal, A. (2023) Patchcontrast: Self-supervised pre-training for 3d object detection. arXiv:2308.06985"},{"key":"2313_CR44","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 al. (2020). 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.","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"2313_CR45","doi-asserted-by":"crossref","unstructured":"Tian, X., Ran, H., Wang, Y., & Zhao, H. (2023). Geomae: Masked geometric target prediction for self-supervised point cloud pre-training. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13570\u201313580.","DOI":"10.1109\/CVPR52729.2023.01304"},{"key":"2313_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, X., You, Y., Li, L. E., Hariharan, B., Campbell, M., Weinberger, K. Q., & Chao, W. L. (2020). Train in Germany, test in the USA: Making 3d object detectors generalize. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11713\u201311723.","DOI":"10.1109\/CVPR42600.2020.01173"},{"key":"2313_CR47","doi-asserted-by":"crossref","unstructured":"Wang, Y., Mao, Q., Zhu, H., Deng, J., Zhang, Y., Ji, J., Li, H., & Zhang, Y. (2023). Multi-modal 3d object detection in autonomous driving: A survey. International Journal of Computer Vision, pp. 1\u201331.","DOI":"10.1007\/s11263-023-01784-z"},{"key":"2313_CR48","doi-asserted-by":"crossref","unstructured":"Wei, C., Fan, H., Xie, S., Wu, C. Y., Yuille, A., & Feichtenhofer, C. (2022). Masked feature prediction for self-supervised visual pre-training. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14668\u201314678.","DOI":"10.1109\/CVPR52688.2022.01426"},{"key":"2313_CR49","doi-asserted-by":"crossref","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C. R., Guibas, L., & Litany, O. (2020). Pointcontrast: Unsupervised pre-training for 3d point cloud understanding. in Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part III 16. Springer, pp. 574\u2013591.","DOI":"10.1007\/978-3-030-58580-8_34"},{"key":"2313_CR50","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., Cao, Y., Lin, Y., Bao, J., Yao, Z., Dai, Q., & Hu, H. (2022). Simmim: A simple framework for masked image modeling. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9653\u20139663.","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"2313_CR51","doi-asserted-by":"crossref","unstructured":"Xu, R., Wang, T., Zhang, W., Chen, R., Cao, J., Pang, J., & Lin, D. (2023). Mv-jar: Masked voxel jigsaw and reconstruction for lidar-based self-supervised pre-training. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13445\u201313454.","DOI":"10.1109\/CVPR52729.2023.01292"},{"key":"2313_CR52","doi-asserted-by":"crossref","unstructured":"Yang, H., He, T., Liu, J., Chen, H., Wu, B., Lin, B., He, X., & Ouyang, W. (2023). Gd-mae: generative decoder for mae pre-training on lidar point clouds. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9403\u20139414.","DOI":"10.1109\/CVPR52729.2023.00907"},{"key":"2313_CR53","doi-asserted-by":"crossref","unstructured":"Yang, J., Shi, S., Wang, Z., Li, H., & Qi, X. (2021). St3d: Self-training for unsupervised domain adaptation on 3d object detection. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, p. 1.","DOI":"10.1109\/TPAMI.2022.3216606"},{"key":"2313_CR54","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., & Jia, J. (2020). 3dssd: Point-based 3d single stage object detector. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11040\u201311048.","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"2313_CR55","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., & Jia, J. (2019). Std: Sparse-to-dense 3d object detector for point cloud. in Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1951\u20131960.","DOI":"10.1109\/ICCV.2019.00204"},{"issue":"10","key":"2313_CR56","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. (2018). Second: Sparsely embedded convolutional detection. Sensors, 18(10), 3337.","journal-title":"Sensors"},{"key":"2313_CR57","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., & Krahenbuhl, P. (2021). Center-based 3d object detection and tracking. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11784\u201311793.","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"2313_CR58","doi-asserted-by":"crossref","unstructured":"Yin, J., Zhou, D., Zhang, L., Fang, J., Xu, C. Z., Shen, J., & Wang, W. (2022). Proposalcontrast: Unsupervised pre-training for lidar-based 3d object detection. in European Conference on Computer Vision, Springer, pp. 17\u201333.","DOI":"10.1007\/978-3-031-19842-7_2"},{"key":"2313_CR59","doi-asserted-by":"crossref","unstructured":"Yu, X., Tang, L., Rao, Y., Huang, T., Zhou, J., & Lu, J. (2022). Point-bert: Pre-training 3d point cloud transformers with masked point modeling. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19313\u201319322.","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"2313_CR60","unstructured":"Zbontar, J., Jing, L., Misra, I., LeCun, Y., & Deny, S. (2021). Barlow twins: Self-supervised learning via redundancy reduction. in International Conference on Machine Learning, PMLR, pp. 12310\u201312320."},{"key":"2313_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, L., & Zhu, Z. (2019). Unsupervised feature learning for point cloud understanding by contrasting and clustering using graph convolutional neural networks. in International Conference on 3D Vision (3DV). IEEE, pp. 395\u2013404.","DOI":"10.1109\/3DV.2019.00051"},{"key":"2313_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Girdhar, R., Joulin, A., & Misra, I. (2021b). Self-supervised pretraining of 3d features on any point-cloud. in Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10252\u201310263.","DOI":"10.1109\/ICCV48922.2021.01009"},{"key":"2313_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hou, J., & Yuan, Y. (2023a). A comprehensive study of the robustness for lidar-based 3d object detectors against adversarial attacks. International Journal of Computer Vision, pp. 1\u201333.","DOI":"10.1007\/s11263-023-01934-3"},{"key":"2313_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hu, Q., Xu, G., Ma, Y., Wan, J., & Guo, Y. (2022b). 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.","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"2313_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Huang, D., & Wang, Y. (2021a). Pc-rgnn: Point cloud completion and graph neural network for 3d object detection. in Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3430\u20133437.","DOI":"10.1609\/aaai.v35i4.16456"},{"key":"2313_CR66","unstructured":"Zhang, Y., Lin, J., He, C., Chen, Y., Jia, K., & Zhang, L. (2022c). Masked surfel prediction for self-supervised point cloud learning. arXiv:2207.03111"},{"key":"2313_CR67","unstructured":"Zhang, R., Guo, Z., Gao, P., Fang, R., Zhao, B., Wang, D., Qiao, Y., & Li, H. (2022). Point-m2ae: Multi-scale masked autoencoders for hierarchical point cloud pre-training. Advances in Neural Information Processing Systems, 35, 27061\u201327074."},{"issue":"12","key":"2313_CR68","doi-asserted-by":"publisher","first-page":"3332","DOI":"10.1007\/s11263-023-01869-9","volume":"131","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Zhang, Q., Zhu, Z., Hou, J., & Yuan, Y. (2023). Glenet: Boosting 3d object detectors with generative label uncertainty estimation. International Journal of Computer Vision, 131(12), 3332\u20133352.","journal-title":"International Journal of Computer Vision"},{"key":"2313_CR69","doi-asserted-by":"crossref","unstructured":"Zheng, W., Chen, W., Huang, Y., Zhang, B., Duan, Y., & Lu, J. (2023) Occworld: Learning a 3d occupancy world model for autonomous driving. arXiv:2311.16038","DOI":"10.1007\/978-3-031-72624-8_4"},{"key":"2313_CR70","doi-asserted-by":"crossref","unstructured":"Zhou, Y., & Tuzel, O. (2018). 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.","DOI":"10.1109\/CVPR.2018.00472"},{"key":"2313_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, C., Zhang, Y., Chen, J., & Huang, D. (2023). Octr: Octree-based transformer for 3d object detection. in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5166\u20135175.","DOI":"10.1109\/CVPR52729.2023.00500"}],"updated-by":[{"DOI":"10.1007\/s11263-025-02359-w","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T00:00:00Z","timestamp":1737504000000}}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02313-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02313-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02313-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T06:04:20Z","timestamp":1744869860000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02313-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,11]]},"references-count":71,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,5]]}},"alternative-id":["2313"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02313-2","relation":{"correction":[{"id-type":"doi","id":"10.1007\/s11263-025-02359-w","asserted-by":"object"}]},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,11]]},"assertion":[{"value":"14 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The affiliation of the first author has been corrected","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 January 2025","order":7,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":8,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":9,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s11263-025-02359-w","URL":"https:\/\/doi.org\/10.1007\/s11263-025-02359-w","order":10,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}}]}}