{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:27:31Z","timestamp":1783099651496,"version":"3.54.6"},"reference-count":70,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T00:00:00Z","timestamp":1692057600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T00:00:00Z","timestamp":1692057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001839","name":"University Grants Committee","doi-asserted-by":"publisher","award":["11202320"],"award-info":[{"award-number":["11202320"]}],"id":[{"id":"10.13039\/501100001839","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":[[2023,12]]},"DOI":"10.1007\/s11263-023-01869-9","type":"journal-article","created":{"date-parts":[[2023,8,15]],"date-time":"2023-08-15T13:01:50Z","timestamp":1692104510000},"page":"3332-3352","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":67,"title":["GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation"],"prefix":"10.1007","volume":"131","author":[{"given":"Yifan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qijian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3431-2021","authenticated-orcid":false,"given":"Junhui","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yixuan","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,8,15]]},"reference":[{"key":"1869_CR1","doi-asserted-by":"crossref","unstructured":"Bowman, S., Vilnis, L., Vinyals, O., Dai, A., Jozefowicz, R. & Bengio, S. (2016). Generating sentences from a continuous space. In: proceedings of the 20th SIGNLL conference on computational natural language learning, pp 10\u201321.","DOI":"10.18653\/v1\/K16-1002"},{"key":"1869_CR2","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A. & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European conference on computer vision, pp 213\u2013229.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1869_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B. & Xia, T. (2017). Multi-view 3d object detection network for autonomous driving. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1907\u20131915.","DOI":"10.1109\/CVPR.2017.691"},{"key":"1869_CR4","doi-asserted-by":"crossref","unstructured":"Choi, J., Chun, D., Kim, H. & Lee HJ. (2019). Gaussian yolov3: An accurate and fast object detector using localization uncertainty for autonomous driving. In proceedings of the IEEE international conference on computer vision, vol 2019-Oct, pp 02\u2013511.","DOI":"10.1109\/ICCV.2019.00059"},{"key":"1869_CR5","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.knosys.2012.01.015","volume":"31","author":"SJ Delany","year":"2012","unstructured":"Delany, S. J., Segata, N., & Mac Namee, B. (2012). Profiling instances in noise reduction. Knowledge-Based Systems, 31, 28\u201340.","journal-title":"Knowledge-Based Systems"},{"key":"1869_CR6","doi-asserted-by":"crossref","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y. & Li, H. (2021). Voxel r-cnn: Towards high performance voxel-based 3d object detection. In proceedings of the AAAI conference on artificial intelligence, pp 1201\u20131209.","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"1869_CR7","doi-asserted-by":"crossref","unstructured":"Feng, D., Rosenbaum, L. & Dietmayer, K. (2018). Towards safe autonomous driving: Capture uncertainty in the deep neural network for lidar 3d vehicle detection. In IEEE conference on intelligent transportation systems, pp 3266\u20133273.","DOI":"10.1109\/ITSC.2018.8569814"},{"key":"1869_CR8","doi-asserted-by":"crossref","unstructured":"Feng, D., Rosenbaum, L., Timm, F. & Dietmayer, K. (2019). Leveraging heteroscedastic aleatoric uncertainties for robust real-time lidar 3d object detection. In IEEE intelligent vehicles symposium, pp 1280\u20131287.","DOI":"10.1109\/IVS.2019.8814046"},{"key":"1869_CR9","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.knosys.2015.09.023","volume":"90","author":"LP Garcia","year":"2015","unstructured":"Garcia, L. P., S\u00e1ez, J. A., Luengo, J., Lorena, A. C., de Carvalho, A. C., & Herrera, F. (2015). Using the one-vs-one decomposition to improve the performance of class noise filters via an aggregation strategy in multi-class classification problems. Knowledge-Based Systems, 90, 153\u2013164.","journal-title":"Knowledge-Based Systems"},{"key":"1869_CR10","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P. & Urtasun, R. (2012). Are we ready for autonomous driving? the kitti vision benchmark suite. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3354\u20133361.","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"1869_CR11","unstructured":"Goyal, A., Sordoni, A., C$$\\hat{o}$$t\u00e9, MA., Ke, N. & Bengio, Y. (2017). Z-forcing: Training stochastic recurrent networks. Advances in Neural Information Processing Systems, pp 6714\u20136724."},{"key":"1869_CR12","doi-asserted-by":"crossref","unstructured":"Harakeh, A., Smart, M. & Waslander, SL. (2020). Bayesod: A bayesian approach for uncertainty estimation in deep object detectors. In IEEE international conference on robotics and automation, IEEE, pp 87\u201393.","DOI":"10.1109\/ICRA40945.2020.9196544"},{"key":"1869_CR13","doi-asserted-by":"crossref","unstructured":"He, C., Zeng, H., Huang, J., Hua, XS., & Zhang, L. (2020). Structure aware single-stage 3d object detection from point cloud. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11870\u201311879.","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"1869_CR14","doi-asserted-by":"crossref","unstructured":"He, Y., Zhu, C., Wang, J., Savvides, M., & Zhang, X. (2019). Bounding box regression with uncertainty for accurate object detection. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2888\u20132897.","DOI":"10.1109\/CVPR.2019.00300"},{"key":"1869_CR15","doi-asserted-by":"crossref","unstructured":"Huang, T., Liu, Z., Chen, X., & Bai, X. (2020). Epnet: Enhancing point features with image semantics for 3d object detection. In European conference on computer vision, Springer, pp 35\u201352.","DOI":"10.1007\/978-3-030-58555-6_3"},{"key":"1869_CR16","unstructured":"Kingma, D., & Ba, J. (2015). Adam: A method for stochastic optimization. In international conference on learning representations, pp 1\u201315."},{"key":"1869_CR17","unstructured":"Kingma, D.P., & Welling, M. (2014). Auto-encoding variational bayes. In international conference on learning representations, pp 1\u201314."},{"key":"1869_CR18","doi-asserted-by":"crossref","unstructured":"Lang, A., 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, pp 12689\u201312697.","DOI":"10.1109\/CVPR.2019.01298"},{"key":"1869_CR19","doi-asserted-by":"publisher","first-page":"8569","DOI":"10.1609\/aaai.v33i01.33018569","volume":"33","author":"B Li","year":"2019","unstructured":"Li, B., Sun, Z., & Guo, Y. (2019). Supervae: superpixelwise variational autoencoder for salient object detection. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 8569\u20138576.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"1869_CR20","doi-asserted-by":"crossref","unstructured":"Li, J., Song, Y., Zhang, H., Chen, D., Shi, S., Zhao, D., & Yan, R. (2018). Generating classical chinese poems via conditional variational autoencoder and adversarial training. In proceedings of the 2018 conference on empirical methods in natural language processing, pp 3890\u20133900.","DOI":"10.18653\/v1\/D18-1423"},{"key":"1869_CR21","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Li, J., Tang, J., & Yang, J. (2021). Generalized focal loss v2: Learning reliable localization quality estimation for dense object detection. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11632\u201311641.","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"1869_CR22","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Chen, Y., Hu, R., & Urtasun, R. (2019). Multi-task multi-sensor fusion for 3d object detection. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7345\u20137353.","DOI":"10.1109\/CVPR.2019.00752"},{"key":"1869_CR23","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., & Berg, A.C. (2016). Ssd: Single shot multibox detector. In European conference on computer vision, Springer, pp 21\u201337.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1869_CR24","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.knosys.2017.10.026","volume":"140","author":"J Luengo","year":"2018","unstructured":"Luengo, J., Shim, S. O., Alshomrani, S., Altalhi, A., & Herrera, F. (2018). Cnc-nos: Class noise cleaning by ensemble filtering and noise scoring. Knowledge-Based Systems, 140, 27\u201349.","journal-title":"Knowledge-Based Systems"},{"key":"1869_CR25","doi-asserted-by":"crossref","unstructured":"Mao, J., Niu, M., Bai, H., Liang, X., Xu, H., & Xu, C. (2021a). 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.","DOI":"10.1109\/ICCV48922.2021.00272"},{"key":"1869_CR26","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, pp 3164\u20133173.","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"1869_CR27","doi-asserted-by":"crossref","unstructured":"Meyer, G., & Thakurdesai, N. (2020). Learning an uncertainty-aware object detector for autonomous driving. In IEEE international conference on intelligent robots and systems, pp 10521\u201310527.","DOI":"10.1109\/IROS45743.2020.9341623"},{"key":"1869_CR28","doi-asserted-by":"crossref","unstructured":"Meyer, G.P., Laddha, A., Kee, E., Vallespi-Gonzalez, C., & Wellington, C.K. (2019). Lasernet: An efficient probabilistic 3d object detector for autonomous driving. In: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12677\u201312686.","DOI":"10.1109\/CVPR.2019.01296"},{"key":"1869_CR29","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Eppner, C., & Fox, D. (2019). 6-dof graspnet: Variational grasp generation for object manipulation. In: proceedings of the IEEE\/CVF international conference on computer vision, pp 2901\u20132910.","DOI":"10.1109\/ICCV.2019.00299"},{"key":"1869_CR30","doi-asserted-by":"crossref","unstructured":"Najibi, M., Lai, G., Kundu, A., Lu, Z., Rathod, V., Funkhouser, T., Pantofaru, C., Ross, D., Davis, L., & Fathi, A. (2020). Dops: Learning to detect 3d objects and predict their 3d shapes. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11910\u201311919.","DOI":"10.1109\/CVPR42600.2020.01193"},{"issue":"5","key":"1869_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/cgf.13240","volume":"36","author":"C Nash","year":"2017","unstructured":"Nash, C., & Williams, C. (2017). The shape variational autoencoder: A deep generative model of part-segmented 3d objects. Computer Graphics Forum, 36(5), 1\u201312.","journal-title":"Computer Graphics Forum"},{"key":"1869_CR32","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1613\/jair.1.12125","volume":"70","author":"C Northcutt","year":"2021","unstructured":"Northcutt, C., Jiang, L., & Chuang, I. (2021). Confident learning: Estimating uncertainty in dataset labels. Journal of Artificial Intelligence Research, 70, 1373\u20131411.","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"11","key":"1869_CR33","doi-asserted-by":"publisher","first-page":"3703","DOI":"10.1109\/TMI.2020.3003240","volume":"39","author":"N Painchaud","year":"2020","unstructured":"Painchaud, N., Skandarani, Y., Judge, T., Bernard, O., Lalande, A., & Jodoin, P. M. (2020). Cardiac segmentation with strong anatomical guarantees. IEEE Transactions on Medical Imaging, 39(11), 3703\u20133713.","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"1869_CR34","doi-asserted-by":"crossref","unstructured":"Pang, S., Morris, D., & Radha, H. (2020). Clocs: Camera-lidar object candidates fusion for 3d object detection. In IEEE international conference on intelligent robots and systems, IEEE, pp 10386\u201310393.","DOI":"10.1109\/IROS45743.2020.9341791"},{"key":"1869_CR35","unstructured":"Qi, C.R., Su, H., Mo, K., & Guibas, L.J. (2017). Pointnet: Deep learning on point sets for 3d classification and segmentation. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 652\u2013660."},{"key":"1869_CR36","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\/CVF conference on computer vision and pattern recognition, pp 918\u2013927.","DOI":"10.1109\/CVPR.2018.00102"},{"key":"1869_CR37","doi-asserted-by":"crossref","unstructured":"Sharma, S., Varigonda, P.T., Bindal, P., Sharma, A., & Jain, A. (2019). Monocular 3d human pose estimation by generation and ordinal ranking. In proceedings of the IEEE\/CVF international conference on computer vision, pp 2325\u20132334.","DOI":"10.1109\/ICCV.2019.00241"},{"key":"1869_CR38","doi-asserted-by":"crossref","unstructured":"Sheng, H., Cai, S., Liu, Y., Deng, B., Huang, J., Hua, X.S., & Zhao, M.J. (2021). Improving 3d object detection with channel-wise transformer. In proceedings of the IEEE\/CVF international conference on computer vision, pp 2743\u20132752.","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"1869_CR39","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"},{"key":"1869_CR40","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"},{"issue":"8","key":"1869_CR41","first-page":"2647","volume":"43","author":"S Shi","year":"2020","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., & Li, H. (2020). 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":"1869_CR42","doi-asserted-by":"crossref","unstructured":"Shi, W., & Rajkumar, R. (2020a). 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 1708\u20131716.","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"1869_CR43","doi-asserted-by":"crossref","unstructured":"Shi, W., & Rajkumar, R. (2020b). 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.","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"1869_CR44","doi-asserted-by":"crossref","unstructured":"Smith, L.N. (2017). Cyclical learning rates for training neural networks. In proceedings of the IEEE\/CVF winter conference on applications of computer vision, IEEE, pp 464\u2013472.","DOI":"10.1109\/WACV.2017.58"},{"key":"1869_CR45","unstructured":"Sohn, K., Lee, H., & Yan, X. (2015). Learning structured output representation using deep conditional generative models. In advances in neural information processing systems, pp 3483\u20133491."},{"key":"1869_CR46","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., Vasudevan, V., Han, W., Ngiam, J., Zhao, H., Timofeev, A., Ettinger, S., Krivokon, M., Gao, A., Joshi, A., Zhang, Y., Shlens, J., Chen, Z., & Anguelov, D. (2020). Scalability in perception for autonomous driving: Waymo open dataset. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2443\u20132451.","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"1869_CR47","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., & Le, Q.V. (2020). Efficientdet: Scalable and efficient object detection. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10781\u201310790.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"1869_CR48","doi-asserted-by":"crossref","unstructured":"Varamesh, A., & Tuytelaars, T. (2020). Mixture dense regression for object detection and human pose estimation. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13086\u201313095.","DOI":"10.1109\/CVPR42600.2020.01310"},{"key":"1869_CR49","doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Helou, B., & Beijbom, O. (2020). Pointpainting: Sequential fusion for 3d object detection. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 4604\u20134612.","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"1869_CR50","doi-asserted-by":"crossref","unstructured":"Wang, T., & Wan, X. (2019). T-cvae: Transformer-based conditioned variational autoencoder for story completion. In international joint conference on artificial intelligence, pp 5233\u20135239.","DOI":"10.24963\/ijcai.2019\/727"},{"key":"1869_CR51","doi-asserted-by":"crossref","unstructured":"Wang, Z., Feng, D., Zhou, Y., Rosenbaum, L., Timm, F., Dietmayer, K., Tomizuka, M., & Zhan, W. (2020). Inferring spatial uncertainty in object detection. In IEEE international conference on intelligent robots and systems, IEEE, pp 5792\u20135799.","DOI":"10.1109\/IROS45743.2020.9340798"},{"key":"1869_CR52","doi-asserted-by":"crossref","unstructured":"Xu, Q., Zhou, Y., Wang, W., Qi, CR. & Anguelov, D. (2021). Spg: Unsupervised domain adaptation for 3d object detection via semantic point generation. In proceedings of the IEEE\/CVF international conference on computer vision, pp 15446\u201315456","DOI":"10.1109\/ICCV48922.2021.01516"},{"key":"1869_CR53","doi-asserted-by":"crossref","unstructured":"Yan, X., Yang, J., Sohn, K. & Lee, H. (2016). Attribute2image: Conditional image generation from visual attributes. In European conference on computer vision, Springer, pp 776\u2013791","DOI":"10.1007\/978-3-319-46493-0_47"},{"key":"1869_CR54","doi-asserted-by":"crossref","unstructured":"Yan, X., Rastogi, A., Villegas, R., Sunkavalli, K., Shechtman, E., Hadap, S., Yumer, E. & Lee, H. (2018a). Mt-vae: Learning motion transformations to generate multimodal human dynamics. In European conference on computer vision, pp 265\u2013281","DOI":"10.1007\/978-3-030-01228-1_17"},{"key":"1869_CR55","doi-asserted-by":"publisher","first-page":"3101","DOI":"10.1609\/aaai.v35i4.16419","volume":"35","author":"X Yan","year":"2021","unstructured":"Yan, X., Gao, J., Li, J., Zhang, R., Li, Z., Huang, R., & Cui, S. (2021). Sparse single sweep lidar point cloud segmentation via learning contextual shape priors from scene completion. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 3101\u20133109.","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"10","key":"1869_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":"1869_CR57","doi-asserted-by":"crossref","unstructured":"Yang, B., Luo, W. & Urtasun, R. (2018). Pixor: Real-time 3d object detection from point clouds. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7652\u20137660","DOI":"10.1109\/CVPR.2018.00798"},{"key":"1869_CR58","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"},{"key":"1869_CR59","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":"1869_CR60","doi-asserted-by":"crossref","unstructured":"Yi, L., Zhao, W., Wang, H., Sung, M. & Guibas, L. (2019). Gspn: Generative shape proposal network for 3d instance segmentation in point cloud. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3942\u20133951","DOI":"10.1109\/CVPR.2019.00407"},{"key":"1869_CR61","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":"1869_CR62","doi-asserted-by":"crossref","unstructured":"Yoo, JH., Kim, Y., Kim, J. & Choi, JW. (2020). 3d-cvf: Generating joint camera and lidar features using cross-view spatial feature fusion for 3d object detection. In European conference on computer vision, Springer, pp 720\u2013736","DOI":"10.1007\/978-3-030-58583-9_43"},{"key":"1869_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, B., Xiong, D., Su, J., Duan, H. & Zhang, M. (2016). Variational neural machine translation. In proceedings of the 2016 conference on empirical methods in natural language processing, Association for Computational Linguistics, Austin, Texas, pp 521\u2013530","DOI":"10.18653\/v1\/D16-1050"},{"issue":"3","key":"1869_CR64","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/3446776","volume":"64","author":"C Zhang","year":"2021","unstructured":"Zhang, C., Bengio, S., Hardt, M., Recht, B., & Vinyals, O. (2021). Understanding deep learning (still) requires rethinking generalization. Communications of the ACM, 64(3), 107\u2013115.","journal-title":"Communications of the ACM"},{"key":"1869_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, J., Fan, DP., Dai, Y., Anwar, S., Saleh, FS., Zhang, T. & Barnes, N. (2020). Uc-net: Uncertainty inspired rgb-d saliency detection via conditional variational autoencoders. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 8582\u20138591","DOI":"10.1109\/CVPR42600.2020.00861"},{"key":"1869_CR66","doi-asserted-by":"crossref","unstructured":"Zhao, T., Zhao, R. & Eskenazi, M. (2017). Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. In ACL 2017 - 55th annual meeting of the association for computational linguistics, proceedings of the conference, pp 654\u2013664","DOI":"10.18653\/v1\/P17-1061"},{"key":"1869_CR67","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Chen, S., Jiang, L., Fu, CW. (2021a). Cia-ssd: Confident iou-aware single-stage object detector from point cloud. In proceedings of the AAAI conference on artificial intelligence, pp 3555\u20133562","DOI":"10.1609\/aaai.v35i4.16470"},{"key":"1869_CR68","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Jiang, L., Fu CW. (2021b). Se-ssd: Self-ensembling single-stage object detector from point cloud. In proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 14494\u201314503","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"1869_CR69","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\/CVF conference on computer vision and pattern recognition, pp 4490\u20134499","DOI":"10.1109\/CVPR.2018.00472"},{"key":"1869_CR70","unstructured":"Zhou, Y., Sun, P., Zhang, Y., Anguelov, D., Gao, J., Ouyang, T., Guo, J., Ngiam, J. & Vasudevan, V. (2020). End-to-end multi-view fusion for 3d object detection in lidar point clouds. In conference on robot learning, PMLR, pp 923\u2013932"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01869-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01869-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01869-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T14:10:16Z","timestamp":1698415816000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01869-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,15]]},"references-count":70,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["1869"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01869-9","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,15]]},"assertion":[{"value":"20 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}