{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:40:33Z","timestamp":1780512033429,"version":"3.54.1"},"publisher-location":"Cham","reference-count":73,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729911","type":"print"},{"value":"9783031729928","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"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\/978-3-031-72992-8_2","type":"book-chapter","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:29:02Z","timestamp":1730190542000},"page":"19-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["LabelDistill: Label-Guided Cross-Modal Knowledge Distillation for\u00a0Camera-Based 3D Object Detection"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4042-6570","authenticated-orcid":false,"given":"Sanmin","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9984-2416","authenticated-orcid":false,"given":"Youngseok","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1557-4664","authenticated-orcid":false,"given":"Sihwan","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2679-3280","authenticated-orcid":false,"given":"Hyeonjun","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2590-4845","authenticated-orcid":false,"given":"Dongsuk","family":"Kum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Brazil, G., Liu, X.: M3D-RPN: monocular 3D region proposal network for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9287\u20139296 (2019)","DOI":"10.1109\/ICCV.2019.00938"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"2_CR3","unstructured":"Cao, W., Zhang, Y., Gao, J., Cheng, A., Cheng, K., Cheng, J.: PKD: general distillation framework for object detectors via Pearson correlation coefficient. In: Advances in Neural Information Processing Systems, vol. 35, pp. 15394\u201315406 (2022)"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Chen, D., Li, J., Guizilini, V., Ambrus, R.A., Gaidon, A.: Viewpoint equivariance for multi-view 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9213\u20139222 (2023)","DOI":"10.1109\/CVPR52729.2023.00889"},{"key":"2_CR5","unstructured":"Chen, S., Wang, X., Cheng, T., Zhang, Q., Huang, C., Liu, W.: Polar parametrization for vision-based surround-view 3D detection. arXiv preprint arXiv:2206.10965 (2022)"},{"key":"2_CR6","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F.: Bevdistill: cross-modal BEV distillation for multi-view 3D object detection. In: International Conference on Learning Representations (2023)"},{"key":"2_CR7","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_CR8","unstructured":"Chong, Z., et al.: Monodistill: learning spatial features for monocular 3D object detection. In: International Conference on Learning Representations (2022)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Dai, X., et al.: General instance distillation for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7842\u20137851 (2021)","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Feng, C., Jie, Z., Zhong, Y., Chu, X., Ma, L.: Aedet: azimuth-invariant multi-view 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21580\u201321588 (2023)","DOI":"10.1109\/CVPR52729.2023.02067"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Guizilini, V., Ambrus, R., Pillai, S., Raventos, A., Gaidon, A.: 3D packing for self-supervised monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2485\u20132494 (2020)","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Hahner, M., et al.: LiDAR snowfall simulation for robust 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16364\u201316374 (2022)","DOI":"10.1109\/CVPR52688.2022.01588"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Hahner, M., Sakaridis, C., Dai, D., Van\u00a0Gool, L.: FOG simulation on real lidar point clouds for 3D object detection in adverse weather. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15283\u201315292 (2021)","DOI":"10.1109\/ICCV48922.2021.01500"},{"key":"2_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-030-58595-2_32","volume-title":"Computer Vision \u2013 ECCV 2020","author":"M Hao","year":"2020","unstructured":"Hao, M., Liu, Y., Zhang, X., Sun, J.: LabelEnc: a new intermediate supervision method for object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12370, pp. 529\u2013545. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58595-2_32"},{"key":"2_CR15","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Hong, Y., Dai, H., Ding, Y.: Cross-modality knowledge distillation network for monocular 3D object detection. In: European Conference on Computer Vision, pp. 87\u2013104 (2022)","DOI":"10.1007\/978-3-031-20080-9_6"},{"key":"2_CR17","unstructured":"Huang, J., Huang, G.: Bevdet4d: exploit temporal cues in multi-camera 3D object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"2_CR18","unstructured":"Huang, J., Huang, G., Zhu, Z., Du, D.: Bevdet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"2_CR19","unstructured":"Huang, L., et al.: Leveraging vision-centric multi-modal expertise for 3D object detection. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023)"},{"key":"2_CR20","unstructured":"Huang, P., et al.: TiG-BEV: multi-view BEV 3D object detection via target inner-geometry learning. arXiv preprint arXiv:2212.13979 (2022)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Label-guided auxiliary training improves 3D object detector. In: European Conference on Computer Vision, pp. 684\u2013700 (2022)","DOI":"10.1007\/978-3-031-20077-9_40"},{"key":"2_CR22","unstructured":"Jang, S., Jo, D.U., Hwang, S.J., Lee, D., Ji, D.: STXD: structural and temporal cross-modal distillation for multi-view 3D object detection. In: Thirty-Seventh Conference on Neural Information Processing Systems (2023)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, Y., et al.: Polarformer: multi-camera 3D object detection with polar transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1042\u20131050 (2023)","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Kim, S., Kim, Y., Lee, I.J., Kum, D.: Predict to detect: prediction-guided 3D object detection using sequential images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 18057\u201318066 (2023)","DOI":"10.1109\/ICCV51070.2023.01655"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Klingner, M., et al.: X3KD: knowledge distillation across modalities, tasks and stages for multi-camera 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13343\u201313353 (2023)","DOI":"10.1109\/CVPR52729.2023.01282"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Koh, J., Lee, J., Lee, Y., Kim, J., Choi, J.W.: Mgtanet: encoding sequential lidar points using long short-term motion-guided temporal attention for 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1179\u20131187 (2023)","DOI":"10.1609\/aaai.v37i1.25200"},{"key":"2_CR27","unstructured":"Li, Y., Chen, Y., Qi, X., Li, Z., Sun, J., Jia, J.: Unifying voxel-based representation with transformer for 3D object detection. In: Advances in Neural Information Processing Systems, pp. 18442\u201318455 (2022)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Bao, H., Ge, Z., Yang, J., Sun, J., Li, Z.: Bevstereo: enhancing depth estimation in multi-view 3D object detection with temporal stereo. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1486\u20131494 (2023)","DOI":"10.1609\/aaai.v37i2.25234"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Li, Y., et al.: Bevdepth: acquisition of reliable depth for multi-view 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Bevformer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: European Conference on Computer Vision, pp. 1\u201318 (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Li, Z., Yu, Z., Wang, W., Anandkumar, A., Lu, T., Alvarez, J.M.: FB-BEV: BEV representation from forward-backward view transformations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6919\u20136928 (2023)","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Li, Z., Qu, Z., Zhou, Y., Liu, J., Wang, H., Jiang, L.: Diversity matters: fully exploiting depth clues for reliable monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2791\u20132800 (2022)","DOI":"10.1109\/CVPR52688.2022.00281"},{"key":"2_CR33","unstructured":"Lin, X., Lin, T., Pei, Z., Huang, L., Su, Z.: Sparse4d: multi-view 3D object detection with sparse spatial-temporal fusion. arXiv preprint arXiv:2211.10581 (2022)"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Y., Chen, K., Liu, C., Qin, Z., Luo, Z., Wang, J.: Structured knowledge distillation for semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2604\u20132613 (2019)","DOI":"10.1109\/CVPR.2019.00271"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: PETR: position embedding transformation for multi-view 3D object detection. In: European Conference on Computer Vision, pp. 531\u2013548 (2022)","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: PETRV2: a unified framework for 3D perception from multi-camera images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3262\u20133272 (2023)","DOI":"10.1109\/ICCV51070.2023.00302"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wu, Z., T\u00f3th, R.: Smoke: single-stage monocular 3D object detection via keypoint estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 996\u2013997 (2020)","DOI":"10.1109\/CVPRW50498.2020.00506"},{"key":"2_CR38","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1016\/j.neucom.2021.01.100","volume":"438","author":"Z Liu","year":"2021","unstructured":"Liu, Z., Zhu, L.: Label-guided attention distillation for lane segmentation. Neurocomputing 438, 312\u2013322 (2021)","journal-title":"Neurocomputing"},{"key":"2_CR39","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Geometry uncertainty projection network for monocular 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3111\u20133121 (2021)","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Mostajabi, M., Maire, M., Shakhnarovich, G.: Regularizing deep networks by modeling and predicting label structure. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5629\u20135638 (2018)","DOI":"10.1109\/CVPR.2018.00590"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Kosecka, J.: 3D bounding box estimation using deep learning and geometry. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7074\u20137082 (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: European Conference on Computer Vision, pp. 483\u2013499 (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Park, D., Ambrus, R., Guizilini, V., Li, J., Gaidon, A.: Is pseudo-lidar needed for monocular 3D object detection? In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3142\u20133152 (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"2_CR45","unstructured":"Park, J., et al.: Time will tell: new outlooks and a baseline for temporal multi-view 3D object detection. In: International Conference on Learning Representations (2022)"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Park, W., Kim, D., Lu, Y., Cho, M.: Relational knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3967\u20133976 (2019)","DOI":"10.1109\/CVPR.2019.00409"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: European Conference on Computer Vision, pp. 194\u2013210 (2020)","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Qin, Z., Li, X.: Monoground: detecting monocular 3D objects from the ground. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3793\u20133802 (2022)","DOI":"10.1109\/CVPR52688.2022.00377"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8555\u20138564 (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"2_CR50","unstructured":"Roddick, T., Kendall, A., Cipolla, R.: Orthographic feature transform for monocular 3D object detection. In: The British Machine Vision Conference (2018)"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"issue":"2","key":"2_CR52","doi-asserted-by":"publisher","first-page":"1372","DOI":"10.1109\/TPAMI.2022.3159581","volume":"45","author":"Z Tian","year":"2022","unstructured":"Tian, Z., et al.: Adaptive perspective distillation for semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 1372\u20131387 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR53","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"2_CR54","unstructured":"Wang, T., Xinge, Z., Pang, J., Lin, D.: Probabilistic and geometric depth: detecting objects in perspective. In: Conference on Robot Learning, pp. 1475\u20131485 (2022)"},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"Wang, T., Zhu, X., Pang, J., Lin, D.: FCOS3D: fully convolutional one-stage monocular 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 913\u2013922 (2021)","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"2_CR56","unstructured":"Wang, Y., Guizilini, V.C., Zhang, T., Wang, Y., Zhao, H., Solomon, J.: DETR3D: 3D object detection from multi-view images via 3D-to-2D queries. In: Conference on Robot Learning, pp. 180\u2013191 (2022)"},{"key":"2_CR57","unstructured":"Wang, Y., Solomon, J.M.: Object DGCNN: 3D object detection using dynamic graphs. In: Advances in Neural Information Processing Systems, pp. 20745\u201320758 (2021)"},{"key":"2_CR58","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1007\/978-3-030-58571-6_21","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Wang","year":"2020","unstructured":"Wang, Y., Zhou, W., Jiang, T., Bai, X., Xu, Y.: Intra-class feature variation distillation for semantic segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 346\u2013362. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_21"},{"key":"2_CR59","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, D., Luo, C., Xie, C., Yang, X.: Distillbev: boosting multi-camera 3D object detection with cross-modal knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8637\u20138646 (2023)","DOI":"10.1109\/ICCV51070.2023.00793"},{"key":"2_CR60","doi-asserted-by":"crossref","unstructured":"Xie, Q., Luong, M.T., Hovy, E., Le, Q.V.: Self-training with noisy student improves imagenet classification. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10687\u201310698 (2020)","DOI":"10.1109\/CVPR42600.2020.01070"},{"key":"2_CR61","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: Bevformer V2: adapting modern image backbones to bird\u2019s-eye-view recognition via perspective supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17830\u201317839 (2023)","DOI":"10.1109\/CVPR52729.2023.01710"},{"key":"2_CR62","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: Focal and global knowledge distillation for detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4643\u20134652 (2022)","DOI":"10.1109\/CVPR52688.2022.00460"},{"key":"2_CR63","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_CR64","doi-asserted-by":"crossref","unstructured":"Yuan, L., Tay, F.E., Li, G., Wang, T., Feng, J.: Revisiting knowledge distillation via label smoothing regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3903\u20133911 (2020)","DOI":"10.1109\/CVPR42600.2020.00396"},{"key":"2_CR65","doi-asserted-by":"crossref","unstructured":"Zeng, J., et al.: Distilling focal knowledge from imperfect expert for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 992\u20131001 (2023)","DOI":"10.1109\/CVPR52729.2023.00102"},{"key":"2_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, H., Yang, D., Yurtsever, E., Redmill, K.A., \u00d6zg\u00fcner, \u00dc.: Faraway-frustum: dealing with lidar sparsity for 3D object detection using fusion. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 2646\u20132652 (2021)","DOI":"10.1109\/ITSC48978.2021.9564990"},{"key":"2_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, L., Dong, R., Tai, H.S., Ma, K.: Pointdistiller: structured knowledge distillation towards efficient and compact 3D detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21791\u201321801 (2023)","DOI":"10.1109\/CVPR52729.2023.02087"},{"key":"2_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, P., Kang, Z., Yang, T., Zhang, X., Zheng, N., Sun, J.: LGD: label-guided self-distillation for object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3309\u20133317 (2022)","DOI":"10.1609\/aaai.v36i3.20240"},{"key":"2_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: QD-BEV: quantization-aware view-guided distillation for multi-view 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3825\u20133835 (2023)","DOI":"10.1109\/ICCV51070.2023.00354"},{"key":"2_CR70","unstructured":"Zhao, H., Zhang, Q., Zhao, S., Zhang, J., Tao, D.: Bevsimdet: simulated multi-modal distillation in bird\u2019s-eye view for multi-view 3D object detection. arXiv preprint arXiv:2303.16818 (2023)"},{"key":"2_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, S., Liu, W., Hu, C., Zhou, S., Ma, C.: Unidistill: a universal cross-modality knowledge distillation framework for 3D object detection in bird\u2019s-eye view. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5116\u20135125 (2023)","DOI":"10.1109\/CVPR52729.2023.00495"},{"key":"2_CR72","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"2_CR73","unstructured":"Zhu, B., Jiang, Z., Zhou, X., Li, Z., Yu, G.: Class-balanced grouping and sampling for point cloud 3D object detection. arXiv preprint arXiv:1908.09492 (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72992-8_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T08:41:03Z","timestamp":1730191263000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72992-8_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"ISBN":["9783031729911","9783031729928"],"references-count":73,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72992-8_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"30 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}