{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T06:40:17Z","timestamp":1776494417569,"version":"3.51.2"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s11263-026-02755-w","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T09:59:46Z","timestamp":1772791186000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Object-Scene-Camera Decomposition and Recomposition for Data Efficient Monocular 3D Object Detection"],"prefix":"10.1007","volume":"134","author":[{"given":"Zhaonian","family":"Kuang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0525-5059","authenticated-orcid":false,"given":"Meng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhu","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Hua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"key":"2755_CR1","doi-asserted-by":"crossref","unstructured":"Caesar, H., Bankiti, V., Lang, A. H., Vora, S., Liong, V. E., Xu, Q., & 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":"2755_CR2","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tai, L., Sun, K., & Li, M. (2020). Monopair: Monocular 3d object detection using pairwise spatial relationships. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 12093\u201312102).","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"2755_CR3","unstructured":"Chong, Z., Ma, X., Zhang, H., Yue, Y., Li, H., Wang, Z., & Ouyang, W. (2022). Monodistill: Learning spatial features for monocular 3d object detection. arXiv preprint arXiv:2201.10830."},{"key":"2755_CR4","doi-asserted-by":"crossref","unstructured":"Dijk, T. V., & Croon, G. D. (2019). How do neural networks see depth in single images?. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 2183\u20132191).","DOI":"10.1109\/ICCV.2019.00227"},{"issue":"10","key":"2755_CR5","doi-asserted-by":"publisher","first-page":"9925","DOI":"10.1109\/TCSVT.2024.3405992","volume":"34","author":"R Ding","year":"2024","unstructured":"Ding, R., Yang, M., & Zheng, N. (2024). Selective transfer learning of cross-modality distillation for monocular 3d object detection. IEEE Transactions on Circuits and Systems for Video Technology, 34(10), 9925\u20139938.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2755_CR6","doi-asserted-by":"crossref","unstructured":"Dvornik, N., Mairal, J., & Schmid, C. (2018). Modeling visual context is key to augmenting object detection datasets. In Proceedings of the European Conference on Computer Vision (ECCV), (pp. 364\u2013380).","DOI":"10.1007\/978-3-030-01258-8_23"},{"key":"2755_CR7","doi-asserted-by":"crossref","unstructured":"Fang, H. S., Sun, J., Wang, R., Gou, M., Li, Y. L., & Lu, C. (2019). Instaboost: Boosting instance segmentation via probability map guided copy-pasting. In Proceedings of the IEEE\/CVF international conference on computer vision, (pp 682\u2013691).","DOI":"10.1109\/ICCV.2019.00077"},{"key":"2755_CR8","doi-asserted-by":"crossref","unstructured":"Fang, J., Zuo, X., Zhou, D., Jin, S., Wang, S., & Zhang, L. (2021). Lidar-aug: A general rendering-based augmentation framework for 3d object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 4710\u20134720).","DOI":"10.1109\/CVPR46437.2021.00468"},{"key":"2755_CR9","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, (pp. 3354\u20133361. IEEE).","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"2755_CR10","doi-asserted-by":"publisher","first-page":"17057","DOI":"10.52202\/075280-0746","volume":"36","author":"Y Ge","year":"2023","unstructured":"Ge, Y., Yu, H. X., Zhao, C., Guo, Y., Huang, X., Ren, L., & Wu, J. (2023). 3d copy-paste: Physically plausible object insertion for monocular 3d detection. Advances in Neural Information Processing Systems, 36, 17057\u201317071.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2755_CR11","doi-asserted-by":"crossref","unstructured":"Hong, Y., Dai, H., & Ding, Y. (2022). Cross-modality knowledge distillation network for monocular 3d object detection. In European Conference on Computer Vision, (pp. 87\u2013104. Springer).","DOI":"10.1007\/978-3-031-20080-9_6"},{"key":"2755_CR12","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., & Du, D. (2021). Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790."},{"key":"2755_CR13","doi-asserted-by":"crossref","unstructured":"Huang, K. C., Wu, T. H., Su, H. T., & Hsu, W. H. (2022). Monodtr: Monocular 3d object detection with depth-aware transformer. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, (pp. 4012\u20134021).","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"2755_CR14","doi-asserted-by":"publisher","first-page":"6570","DOI":"10.1109\/TIP.2023.3333225","volume":"32","author":"C Huang","year":"2023","unstructured":"Huang, C., He, T., Ren, H., Wang, W., Lin, B., & Cai, D. (2023). Obmo: One bounding box multiple objects for monocular 3d object detection. IEEE Transactions on Image Processing, 32, 6570\u20136581.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"7","key":"2755_CR15","doi-asserted-by":"publisher","first-page":"3877","DOI":"10.1007\/s11263-025-02351-4","volume":"133","author":"L Huang","year":"2025","unstructured":"Huang, L., Wang, H., Zeng, J., Zhang, S., Cao, L., Yan, J., & Li, H. (2025). Lidar-guided geometric pretraining for vision-centric 3d object detection. International Journal of Computer Vision, 133(7), 3877\u20133890.","journal-title":"International Journal of Computer Vision"},{"key":"2755_CR16","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.-Y. & et\u00a0al. (2023). Segment anything. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 4015\u20134026).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"2755_CR17","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, (pp. 12697\u201312705).","DOI":"10.1109\/CVPR.2019.01298"},{"key":"2755_CR18","doi-asserted-by":"crossref","unstructured":"Li, Z., Jia, J., & Shi, Y. (2024). Monolss: Learnable sample selection for monocular 3d detection. In 2024 International Conference on 3D Vision (3DV), (pp. 1125\u20131135. IEEE).","DOI":"10.1109\/3DV62453.2024.00088"},{"key":"2755_CR19","doi-asserted-by":"crossref","unstructured":"Li, L., Lian, Q., Wang, L., Ma, N., & Chen, Y.-C. (2023a). Lift3d: Synthesize 3d training data by lifting 2d gan to 3d generative radiance field. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 332\u2013341).","DOI":"10.1109\/CVPR52729.2023.00040"},{"key":"2755_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., Qu, Z., Zhou, Y., Liu, J., Wang, H., & Jiang, L. (2022b). 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).","DOI":"10.1109\/CVPR52688.2022.00281"},{"key":"2755_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., Qiao, Y., & Dai, J. (2022a). Bevformer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In European conference on computer vision, (pp. 1\u201318. Springer).","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"2755_CR22","doi-asserted-by":"crossref","unstructured":"Lian, Q., Ye, B., Xu, R., Yao, W., & Zhang, T. (2022). Exploring geometric consistency for monocular 3d object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp 1685\u20131694).","DOI":"10.1109\/CVPR52688.2022.00173"},{"key":"2755_CR23","doi-asserted-by":"publisher","first-page":"1477","DOI":"10.1609\/aaai.v37i2.25233","volume":"37","author":"Y Li","year":"2023","unstructured":"Li, Y., Ge, Z., Guanyi, Yu., Yang, J., Wang, Z., Shi, Y., Sun, J., & Li, Z. (2023). Bevdepth: Acquisition of reliable depth for multi-view 3d object detection. In Proceedings of the AAAI Conference on Artificial Intelligence, 37, 1477\u20131485.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2755_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wang, T., Zhang, X., & Sun, J. (2022b). Petr: Position embedding transformation for multi-view 3d object detection. In European conference on computer vision, (pp. 531\u2013548. Springer).","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"2755_CR25","doi-asserted-by":"publisher","first-page":"1810","DOI":"10.1609\/aaai.v36i2.20074","volume":"36","author":"X Liu","year":"2022","unstructured":"Liu, X., Xue, N., & Tianfu, W. (2022). Learning auxiliary monocular contexts helps monocular 3d object detection. In Proceedings of the AAAI Conference on Artificial Intelligence, 36, 1810\u20131818.","journal-title":"In Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"2755_CR26","doi-asserted-by":"crossref","unstructured":"Lu, Y., Ma, X., Yang, L., Zhang, T., Liu, Y., Chu, Q., Yan, J., & Ouyang, W. (2021). Geometry uncertainty projection network for monocular 3d object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 3111\u20133121).","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"2755_CR27","doi-asserted-by":"crossref","unstructured":"Ma, X., Zhang, Y., Xu, D., Zhou, D., Yi, S., Li, H., & Ouyang, W. (2021) Delving into localization errors for monocular 3d object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp 4721\u20134730).","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"2755_CR28","doi-asserted-by":"crossref","unstructured":"Maggiolino, G., Ahmad, A., Cao, J., & Kitani, K. (2023). Deep oc-sort: Multi-pedestrian tracking by adaptive re-identification. In 2023 IEEE International Conference on Image Processing (ICIP), (pp 3025\u20133029. IEEE).","DOI":"10.1109\/ICIP49359.2023.10222576"},{"key":"2755_CR29","doi-asserted-by":"crossref","unstructured":"Min, Z., Zhuang, B., Schulter, S., Liu, B., Dunn, E., & Chandraker, M. (2023). Neurocs: Neural nocs supervision for monocular 3d object localization. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 21404\u201321414).","DOI":"10.1109\/CVPR52729.2023.02050"},{"key":"2755_CR30","doi-asserted-by":"crossref","unstructured":"Parihar, R., Sarkar, S., Vora, S., Kundu, J.N., & Babu, R. V. (2025). Monoplace3d: Learning 3d-aware object placement for 3d monocular detection. In Proceedings of the Computer Vision and Pattern Recognition Conference, (pp. 6531\u20136541).","DOI":"10.1109\/CVPR52734.2025.00612"},{"key":"2755_CR31","doi-asserted-by":"crossref","unstructured":"Peng, L., Liu, F., Yu, Z., Yan, S., Deng, D., Yang, Z., Liu, H., & Cai, D. (2022a). Lidar point cloud guided monocular 3d object detection. In European conference on computer vision, (pp 123\u2013139. Springer).","DOI":"10.1007\/978-3-031-19769-7_8"},{"key":"2755_CR32","doi-asserted-by":"crossref","unstructured":"Peng, L., Wu, X., Yang, Z., Liu, H., & Cai, D. (2022b). Did-m3d: Decoupling instance depth for monocular 3d object detection. In European Conference on Computer Vision, (pp. 71\u201388. Springer).","DOI":"10.1007\/978-3-031-19769-7_5"},{"key":"2755_CR33","doi-asserted-by":"crossref","unstructured":"Peng, L., Xu, J., Cheng, H., Yang, Z., Wu, X., Qian, W., Wang, W., Wu, B., & Cai, D. (2024). Learning occupancy for monocular 3d object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 10281\u201310292).","DOI":"10.1109\/CVPR52733.2024.00979"},{"key":"2755_CR34","doi-asserted-by":"crossref","unstructured":"Pu, F., Wang, Y., Deng, J., & Yang, W. (2025). Monodgp: Monocular 3D object detection with decoupled-query and geometry-error priors. In Proceedings of the Computer Vision and Pattern Recognition Conference, (pp. 6520\u20136530).","DOI":"10.1109\/CVPR52734.2025.00611"},{"issue":"8","key":"2755_CR35","doi-asserted-by":"publisher","first-page":"7326","DOI":"10.1109\/LRA.2024.3414272","volume":"9","author":"J Qiao","year":"2024","unstructured":"Qiao, J., Liu, B., Yang, J., Wang, B., Xiu, S., Du, X., & Nie, X. (2024). MonoSample: Synthetic 3D data augmentation method in monocular 3D object detection. IEEE Robotics and Automation Letters, 9(8), 7326\u20137332.","journal-title":"IEEE Robotics and Automation Letters"},{"key":"2755_CR36","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., & Waslander, S. L. (2021). Categorical depth distribution network for monocular 3d object detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8555-8564).","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"2755_CR37","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."},{"issue":"7","key":"2755_CR38","doi-asserted-by":"publisher","first-page":"4817","DOI":"10.1007\/s11263-025-02404-8","volume":"133","author":"H Sheng","year":"2025","unstructured":"Sheng, H., Cai, S., Zhao, N., Deng, B., Liang, Q., Zhao, M.-J., & Ye, J. (2025). Ct3d++: Improving 3d object detection with keypoint-induced channel-wise transformer. International Journal of Computer Vision, 133(7), 4817\u20134836.","journal-title":"International Journal of Computer Vision"},{"issue":"2","key":"2755_CR39","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"},{"key":"2755_CR40","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. (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":"2755_CR41","doi-asserted-by":"crossref","unstructured":"Suvorov, R., Logacheva, E., Mashikhin, A., Remizova, A., Ashukha, A., Silvestrov, A., Kong, N., Goka, H., Park, K., & Lempitsky, V. (2022). Resolution-robust large mask inpainting with fourier convolutions. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision, (pp. 2149\u20132159).","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"2755_CR42","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., & He, T. (2019). Fcos: Fully convolutional one-stage object detection. In Proceedings of the IEEE\/CVF international conference on computer vision, (pp. 9627\u20139636).","DOI":"10.1109\/ICCV.2019.00972"},{"key":"2755_CR43","doi-asserted-by":"crossref","unstructured":"Tong, W., Xie, J., Li, T., Deng, H., Geng, X., Zhou, R., Yang, D., Dai, B., Lu, L., & Li, H. (2023). 3d data augmentation for driving scenes on camera. arXiv preprint arXiv:2303.10340.","DOI":"10.1007\/978-981-97-8508-7_4"},{"key":"2755_CR44","doi-asserted-by":"crossref","unstructured":"Wang, J., Li, F., Lv, S., He, L., & Shen, C. (2025). Physically realizable adversarial creating attack against vision-based BEV space 3D object detection. IEEE Transactions on Image Processing.","DOI":"10.1109\/TIP.2025.3526056"},{"key":"2755_CR45","unstructured":"Wang, H., Wang, Q., Yang, F., Zhang, W., & Zuo, W. (2019). Data augmentation for object detection via progressive and selective instance-switching. arXiv preprint arXiv:1906.00358."},{"key":"2755_CR46","unstructured":"Wang, T., Xinge, Z. H. U., Pang, J., & Lin, D. (2022). Probabilistic and geometric depth: Detecting objects in perspective. In Conference on Robot Learning (pp. 1475-1485). PMLR."},{"issue":"5","key":"2755_CR47","doi-asserted-by":"publisher","first-page":"3753","DOI":"10.1109\/TPAMI.2023.3346466","volume":"46","author":"H Wang","year":"2023","unstructured":"Wang, H., Yang, M., & Zheng, N. (2023). G2-monodepth: A general framework of generalized depth inference from monocular rgb+ x data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(5), 3753\u20133771.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2755_CR48","doi-asserted-by":"crossref","unstructured":"Wen, Y., Zhao, Y., Liu, Y., Jia, F., Wang, Y., Luo, C., Zhang, C., Wang, T., Sun, X., & Zhang, X. (2024). Panacea: Panoramic and controllable video generation for autonomous driving. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 6902\u20136912).","DOI":"10.1109\/CVPR52733.2024.00659"},{"key":"2755_CR49","doi-asserted-by":"crossref","unstructured":"Wu, Y., Li, R., Qin, Z., Zhao, X., & Li, X. (2024). Heightformer: Explicit height modeling without extra data for camera-only 3d object detection in bird\u2019s eye view. IEEE Transactions on Image Processing.","DOI":"10.1109\/TIP.2024.3427701"},{"key":"2755_CR50","doi-asserted-by":"crossref","unstructured":"Yan, L., Yan, P., Xiong, S., Xiang, X., & Tan, Y. (2024). Monocd: Monocular 3d object detection with complementary depths. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 10248-10257).","DOI":"10.1109\/CVPR52733.2024.00976"},{"key":"2755_CR51","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, X., Zhang, W., Tan, X., Lu, J., Wang, J., Ding, E., & Zhao, C. (2025). Fusion4dal: Offline multi-modal 3d object detection for 4d auto-labeling. International Journal of Computer Vision, (pp. 1\u201319).","DOI":"10.1007\/s11263-025-02370-1"},{"issue":"11","key":"2755_CR52","doi-asserted-by":"publisher","first-page":"6832","DOI":"10.1109\/TCSVT.2023.3270728","volume":"33","author":"L Yang","year":"2023","unstructured":"Yang, L., Zhang, X., Li, J., Wang, L., Zhu, M., Zhang, C., & Liu, H. (2023). Mix-teaching: A simple, unified and effective semi-supervised learning framework for monocular 3d object detection. IEEE Transactions on Circuits and Systems for Video Technology, 33(11), 6832\u20136844.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2755_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, J., Li, J., Lin, X., Zhang, W., Tan, X., Han, J., Ding, E., Wang, J., & Li, G. (2024a). Decoupled pseudo-labeling for semi-supervised monocular 3d object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 16923\u201316932).","DOI":"10.1109\/CVPR52733.2024.01601"},{"key":"2755_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, J., & Zhou, J. (2021). Objects are different: Flexible monocular 3d object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, (pp. 3289\u20133298).","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"2755_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, R., Qiu, H., Wang, T., Guo, Z., Cui, Z., Qiao, Y., Li, H., & Gao, P. (2023). Monodetr: Depth-guided transformer for monocular 3d object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, (pp. 9155\u20139166).","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"2755_CR56","unstructured":"Zhang, Y., Zhu, Z., Zheng, W., Huang, J., Huang, G., Zhou, J., & Lu, J. (2022). Beverse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving. arXiv preprint arXiv:2205.09743."},{"issue":"5","key":"2755_CR57","doi-asserted-by":"publisher","first-page":"2783","DOI":"10.1007\/s11263-024-02313-2","volume":"133","author":"Y Zhang","year":"2025","unstructured":"Zhang, Y., Chen, J., & Huang, D. (2025). Cmae-3d: Contrastive masked autoencoders for self-supervised 3d object detection. International Journal of Computer Vision, 133(5), 2783\u20132804.","journal-title":"International Journal of Computer Vision"},{"issue":"5","key":"2755_CR58","doi-asserted-by":"publisher","first-page":"1592","DOI":"10.1007\/s11263-023-01934-3","volume":"132","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Hou, J., & Yuan, Y. (2024). A comprehensive study of the robustness for lidar-based 3d object detectors against adversarial attacks. International Journal of Computer Vision, 132(5), 1592\u20131624.","journal-title":"International Journal of Computer Vision"},{"key":"2755_CR59","unstructured":"Zhou, X., Wang, De., & Kr\u00e4henb\u00fchl, P. (2019). Objects as points. arXiv preprint arXiv:1904.07850."},{"issue":"12","key":"2755_CR60","doi-asserted-by":"publisher","first-page":"10114","DOI":"10.1109\/TPAMI.2021.3136899","volume":"44","author":"Y Zhou","year":"2021","unstructured":"Zhou, Y., He, Y., Zhu, H., Wang, C., Li, H., & Jiang, Q. (2021). Monoef: Extrinsic parameter free monocular 3d object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(12), 10114\u201310128.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02755-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02755-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02755-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T05:44:22Z","timestamp":1776491062000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02755-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":60,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2755"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02755-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]},"assertion":[{"value":"22 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"155"}}