{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T17:18:40Z","timestamp":1743009520068,"version":"3.40.3"},"publisher-location":"Cham","reference-count":87,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730061"},{"type":"electronic","value":"9783031730078"}],"license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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\/978-3-031-73007-8_19","type":"book-chapter","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T19:02:40Z","timestamp":1727722960000},"page":"322-341","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DA-BEV: Unsupervised Domain Adaptation for\u00a0Bird\u2019s Eye View Perception"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9921-2043","authenticated-orcid":false,"given":"Kai","family":"Jiang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8681-0471","authenticated-orcid":false,"given":"Jiaxing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8310-024X","authenticated-orcid":false,"given":"Weiying","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0851-6565","authenticated-orcid":false,"given":"Jie","family":"Lei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunsong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8264-6117","authenticated-orcid":false,"given":"Ling","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6766-2506","authenticated-orcid":false,"given":"Shijian","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,1]]},"reference":[{"key":"19_CR1","unstructured":"Acuna, D., Philion, J., Fidler, S.: Towards optimal strategies for training self-driving perception models in simulation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 1686\u20131699 (2021)"},{"key":"19_CR2","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1007\/978-3-031-19839-7_26","volume-title":"ECCV 2022","author":"AK Akan","year":"2022","unstructured":"Akan, A.K., G\u00fcney, F.: StretchBEV: stretching future instance prediction spatially and temporally. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13698, pp. 444\u2013460. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_26"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Antonello, M., Carraro, M., Pierobon, M., Menegatti, E.: Fast and robust detection of fallen people from a mobile robot. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4159\u20134166. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206276"},{"key":"19_CR4","doi-asserted-by":"crossref","unstructured":"Bai, X., et al.: Transfusion: robust lidar-camera fusion for 3D object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1090\u20131099 (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Barrera, A., Beltr\u00e1n, J., Guindel, C., Iglesias, J.A., Garc\u00eda, F.: Cycle and semantic consistent adversarial domain adaptation for reducing simulation-to-real domain shift in lidar bird\u2019s eye view. In: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pp. 3081\u20133086. IEEE (2021)","DOI":"10.1109\/ITSC48978.2021.9564553"},{"key":"19_CR6","unstructured":"Bartoccioni, F., Zablocki, \u00c9., Bursuc, A., P\u00e9rez, P., Cord, M., Alahari, K.: LaRa: latents and rays for multi-camera bird\u2019s-eye-view semantic segmentation. In: Conference on Robot Learning, pp. 1663\u20131672. PMLR (2023)"},{"key":"19_CR7","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":"19_CR8","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1007\/978-3-031-19839-7_32","volume-title":"ECCV 2022","author":"L Chen","year":"2022","unstructured":"Chen, L., et al.: PersFormer: 3D lane detection via perspective transformer and the OpenLane benchmark. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13698, pp. 550\u2013567. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_32"},{"key":"19_CR9","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":"19_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, S., Shen, X., Jia, J.: DSGN: deep stereo geometry network for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12536\u201312545 (2020)","DOI":"10.1109\/CVPR42600.2020.01255"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: AutoAlign: pixel-instance feature aggregation for multi-modal 3D object detection. arXiv preprint arXiv:2201.06493 (2022)","DOI":"10.24963\/ijcai.2022\/116"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F.: AutoAlignV2: deformable feature aggregation for dynamic multi-modal 3D object detection. arXiv preprint arXiv:2207.10316 (2022)","DOI":"10.1007\/978-3-031-20074-8_36"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Z., Li, Z., Zhang, S., Fang, L., Jiang, Q., Zhao, F.: Graph-DETR3D: rethinking overlapping regions for multi-view 3D object detection. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5999\u20136008 (2022)","DOI":"10.1145\/3503161.3547859"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Z., Luo, Y., Wang, Z., Baktashmotlagh, M., Huang, Z.: Revisiting domain-adaptive 3D object detection by reliable, diverse and class-balanced pseudo-labeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3714\u20133726 (2023)","DOI":"10.1109\/ICCV51070.2023.00344"},{"key":"19_CR15","unstructured":"Ganin, Y., et al.: Domain-adversarial training of neural networks. J. Mach. Learn. Res. 17(1), 2096\u20132030 (2016)"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Gao, Z., Huang, K., Zhang, R., Liu, D., Ma, J.: Towards better robustness against common corruptions for unsupervised domain adaptation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 18882\u201318893 (2023)","DOI":"10.1109\/ICCV51070.2023.01731"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Garnett, N., Cohen, R., Pe\u2019er, T., Lahav, R., Levi, D.: 3D-LaneNet: end-to-end 3D multiple lane detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2921\u20132930 (2019)","DOI":"10.1109\/ICCV.2019.00301"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Gong, R., Li, W., Chen, Y., Gool, L.V.: DLOW: domain flow for adaptation and generalization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2477\u20132486 (2019)","DOI":"10.1109\/CVPR.2019.00258"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Guo, X., Shi, S., Wang, X., Li, H.: Liga-stereo: learning lidar geometry aware representations for stereo-based 3D detector. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3153\u20133163 (2021)","DOI":"10.1109\/ICCV48922.2021.00314"},{"issue":"10","key":"19_CR20","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1177\/0278364908096316","volume":"27","author":"JS Gutmann","year":"2008","unstructured":"Gutmann, J.S., Fukuchi, M., Fujita, M.: 3D perception and environment map generation for humanoid robot navigation. Int. J. Robot. Res. 27(10), 1117\u20131134 (2008)","journal-title":"Int. J. Robot. Res."},{"key":"19_CR21","unstructured":"Hendy, N., et al.: Fishing net: future inference of semantic heatmaps in grids. arXiv preprint arXiv:2006.09917 (2020)"},{"key":"19_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-030-58571-6_1","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Hou","year":"2020","unstructured":"Hou, Y., Zheng, L., Gould, S.: Multiview detection with feature perspective transformation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 1\u201318. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_1"},{"key":"19_CR23","unstructured":"Houston, J., et al.: One thousand and one hours: self-driving motion prediction dataset. In: Conference on Robot Learning, pp. 409\u2013418. PMLR (2021)"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Hu, A., et al.: Fiery: future instance prediction in bird\u2019s-eye view from surround monocular cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15273\u201315282 (2021)","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"19_CR25","unstructured":"Huang, J., Huang, G.: BEVDet4D: exploit temporal cues in multi-camera 3D object detection. arXiv preprint arXiv:2203.17054 (2022)"},{"key":"19_CR26","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., Du, D.: BEVDet: high-performance multi-camera 3D object detection in bird-eye-view. arXiv preprint arXiv:2112.11790 (2021)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Jamal, M.A., Brown, M., Yang, M.H., Wang, L., Gong, B.: Rethinking class-balanced methods for long-tailed visual recognition from a domain adaptation perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7610\u20137619 (2020)","DOI":"10.1109\/CVPR42600.2020.00763"},{"key":"19_CR28","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, vol.\u00a037, pp. 1042\u20131050 (2023)","DOI":"10.1609\/aaai.v37i1.25185"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Jiao, Y., Jie, Z., Chen, S., Chen, J., Ma, L., Jiang, Y.G.: MSMDFusion: fusing lidar and camera at multiple scales with multi-depth seeds for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21643\u201321652 (2023)","DOI":"10.1109\/CVPR52729.2023.02073"},{"key":"19_CR30","unstructured":"Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Workshop on Challenges in Representation Learning, ICML, vol.\u00a03, p.\u00a02 (2013)"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Lee, Y., Park, J.: CenterMask: real-time anchor-free instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13906\u201313915 (2020)","DOI":"10.1109\/CVPR42600.2020.01392"},{"key":"19_CR32","unstructured":"Li, H., et\u00a0al.: Delving into the devils of bird\u2019s-eye-view perception: a review, evaluation and recipe. arXiv preprint arXiv:2209.05324 (2022)"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Li, Q., Wang, Y., Wang, Y., Zhao, H.: HDMapNet: an online HD map construction and evaluation framework. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 4628\u20134634. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812383"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Li, Y., et\u00a0al.: DeepFusion: lidar-camera deep fusion for multi-modal 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17182\u201317191 (2022)","DOI":"10.1109\/CVPR52688.2022.01667"},{"key":"19_CR35","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, vol.\u00a037, pp. 1477\u20131485 (2023)","DOI":"10.1609\/aaai.v37i2.25233"},{"key":"19_CR36","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1007\/978-3-031-20077-9_15","volume-title":"ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., et al.: Unsupervised domain adaptation for monocular 3D object detection via self-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 245\u2013262. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_15"},{"key":"19_CR37","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-031-20077-9_1","volume-title":"ECCV 2022","author":"Z Li","year":"2022","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 1\u201318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1"},{"key":"19_CR38","unstructured":"Liu, J., et al.: Multi-latent space alignments for unsupervised domain adaptation in multi-view 3D object detection. arXiv preprint arXiv:2211.17126 (2022)"},{"key":"19_CR39","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/978-3-031-19812-0_31","volume-title":"ECCV 2022","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Wang, T., Zhang, X., Sun, J.: PETR: position embedding transformation for multi-view 3D object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13687, pp. 531\u2013548. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_31"},{"key":"19_CR40","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":"19_CR41","unstructured":"Long, M., Cao, Y., Wang, J., Jordan, M.: Learning transferable features with deep adaptation networks. In: International Conference on Machine Learning, pp. 97\u2013105 (2015)"},{"key":"19_CR42","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Loukkal, A., Grandvalet, Y., Drummond, T., Li, Y.: Driving among flatmobiles: bird-eye-view occupancy grids from a monocular camera for holistic trajectory planning. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 51\u201360 (2021)","DOI":"10.1109\/WACV48630.2021.00010"},{"issue":"8","key":"19_CR44","first-page":"3940","volume":"44","author":"Y Luo","year":"2021","unstructured":"Luo, Y., Liu, P., Zheng, L., Guan, T., Yu, J., Yang, Y.: Category-level adversarial adaptation for semantic segmentation using purified features. IEEE Trans. Pattern Anal. Mach. Intell. 44(8), 3940\u20133956 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"19_CR45","unstructured":"Ma, Y., et al.: Vision-centric BEV perception: a survey. arXiv preprint arXiv:2208.02797 (2022)"},{"key":"19_CR46","doi-asserted-by":"crossref","unstructured":"Oza, P., Sindagi, V.A., Sharmini, V.V., Patel, V.M.: Unsupervised domain adaptation of object detectors: a survey. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2022.3217046"},{"issue":"3","key":"19_CR47","doi-asserted-by":"publisher","first-page":"4867","DOI":"10.1109\/LRA.2020.3004325","volume":"5","author":"B Pan","year":"2020","unstructured":"Pan, B., Sun, J., Leung, H.Y.T., Andonian, A., Zhou, B.: Cross-view semantic segmentation for sensing surroundings. IEEE Robot. Autom. Lett. 5(3), 4867\u20134873 (2020)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"19_CR48","doi-asserted-by":"crossref","unstructured":"Peng, L., Chen, Z., Fu, Z., Liang, P., Cheng, E.: BEVSegFormer: bird\u2019s eye view semantic segmentation from arbitrary camera rigs. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5935\u20135943 (2023)","DOI":"10.1109\/WACV56688.2023.00588"},{"key":"19_CR49","doi-asserted-by":"crossref","unstructured":"Reiher, L., Lampe, B., Eckstein, L.: A sim2real deep learning approach for the transformation of images from multiple vehicle-mounted cameras to a semantically segmented image in bird\u2019s eye view. In: 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), pp.\u00a01\u20137. IEEE (2020)","DOI":"10.1109\/ITSC45102.2020.9294462"},{"key":"19_CR50","doi-asserted-by":"crossref","unstructured":"Roddick, T., Cipolla, R.: Predicting semantic map representations from images using pyramid occupancy networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11138\u201311147 (2020)","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"19_CR51","unstructured":"Roh, W., et al.: ORA3D: overlap region aware multi-view 3D object detection. arXiv preprint arXiv:2207.00865 (2022)"},{"key":"19_CR52","doi-asserted-by":"crossref","unstructured":"Saha, A., Mendez, O., Russell, C., Bowden, R.: Enabling spatio-temporal aggregation in birds-eye-view vehicle estimation. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 5133\u20135139. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9561169"},{"key":"19_CR53","doi-asserted-by":"crossref","unstructured":"Saleh, K., et al.: Domain adaptation for vehicle detection from bird\u2019s eye view lidar point cloud data. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (2019)","DOI":"10.1109\/ICCVW.2019.00404"},{"issue":"2","key":"19_CR54","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1089\/109493101300117884","volume":"4","author":"MJ Schuemie","year":"2001","unstructured":"Schuemie, M.J., Van Der Straaten, P., Krijn, M., Van Der Mast, C.A.: Research on presence in virtual reality: a survey. Cyberpsychol. Behav. 4(2), 183\u2013201 (2001)","journal-title":"Cyberpsychol. Behav."},{"key":"19_CR55","unstructured":"Shi, Y., et al.: SRCN3D: sparse R-CNN 3D surround-view camera object detection and tracking for autonomous driving. arXiv preprint arXiv:2206.14451 (2022)"},{"key":"19_CR56","doi-asserted-by":"crossref","unstructured":"Song, L., Wu, J., Yang, M., Zhang, Q., Li, Y., Yuan, J.: Stacked homography transformations for multi-view pedestrian detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6049\u20136057 (2021)","DOI":"10.1109\/ICCV48922.2021.00599"},{"key":"19_CR57","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, W., Bao, Q., Fu, Y., Mei, T., Black, M.J.: Putting people in their place: monocular regression of 3D people in depth. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13243\u201313252 (2022)","DOI":"10.1109\/CVPR52688.2022.01289"},{"key":"19_CR58","doi-asserted-by":"crossref","unstructured":"Vora, S., Lang, A.H., Helou, B., Beijbom, O.: Pointpainting: sequential fusion for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4604\u20134612 (2020)","DOI":"10.1109\/CVPR42600.2020.00466"},{"key":"19_CR59","doi-asserted-by":"crossref","unstructured":"Vu, T.H., Jain, H., Bucher, M., Cord, M., P\u00e9rez, P.: Advent: adversarial entropy minimization for domain adaptation in semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2517\u20132526 (2019)","DOI":"10.1109\/CVPR.2019.00262"},{"key":"19_CR60","doi-asserted-by":"crossref","unstructured":"Wang, C., Ma, C., Zhu, M., Yang, X.: Pointaugmenting: cross-modal augmentation for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11794\u201311803 (2021)","DOI":"10.1109\/CVPR46437.2021.01162"},{"key":"19_CR61","doi-asserted-by":"crossref","unstructured":"Wang, L., et\u00a0al.: Multi-modal 3D object detection in autonomous driving: a survey and taxonomy. IEEE Trans. Intell. Veh. (2023)","DOI":"10.1109\/TIV.2023.3264658"},{"key":"19_CR62","unstructured":"Wang, S., Jiang, X., Li, Y.: Focal-PETR: embracing foreground for efficient multi-camera 3D object detection. arXiv preprint arXiv:2212.05505 (2022)"},{"key":"19_CR63","doi-asserted-by":"crossref","unstructured":"Wang, S., et al.: Towards domain generalization for multi-view 3D object detection in bird-eye-view. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13333\u201313342 (2023)","DOI":"10.1109\/CVPR52729.2023.01281"},{"key":"19_CR64","unstructured":"Wang, T., Lian, Q., Zhu, C., Zhu, X., Zhang, W.: MV-FCOS3D++: multi-view camera-only 4D object detection with pretrained monocular backbones. arXiv preprint arXiv:2207.12716 (2022)"},{"key":"19_CR65","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Exploring sequence feature alignment for domain adaptive detection transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1730\u20131738 (2021)","DOI":"10.1145\/3474085.3475317"},{"key":"19_CR66","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Multi-modal 3D object detection in autonomous driving: a survey. Int. J. Comput. Vis. 1\u201331 (2023)","DOI":"10.2139\/ssrn.4398254"},{"key":"19_CR67","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. PMLR (2022)"},{"issue":"5","key":"19_CR68","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3400066","volume":"11","author":"G Wilson","year":"2020","unstructured":"Wilson, G., Cook, D.J.: A survey of unsupervised deep domain adaptation. ACM Trans. Intell. Syst. Technol. (TIST) 11(5), 1\u201346 (2020)","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"key":"19_CR69","unstructured":"Xie, E., et al.: M $$ 2$$ BEV: multi-camera joint 3D detection and segmentation with unified birds-eye view representation. arXiv preprint arXiv:2204.05088 (2022)"},{"key":"19_CR70","doi-asserted-by":"crossref","unstructured":"Xiong, K., et al.: Cape: camera view position embedding for multi-view 3D object detection (2023)","DOI":"10.1109\/CVPR52729.2023.02066"},{"key":"19_CR71","doi-asserted-by":"crossref","unstructured":"Xu, J., Zhang, R., Dou, J., Zhu, Y., Sun, J., Pu, S.: RPVNet: a deep and efficient range-point-voxel fusion network for lidar point cloud segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16024\u201316033 (2021)","DOI":"10.1109\/ICCV48922.2021.01572"},{"key":"19_CR72","unstructured":"Xu, R., Tu, Z., Xiang, H., Shao, W., Zhou, B., Ma, J.: CoBEVT: cooperative bird\u2019s eye view semantic segmentation with sparse transformers. arXiv preprint arXiv:2207.02202 (2022)"},{"key":"19_CR73","doi-asserted-by":"crossref","unstructured":"Yang, C., et\u00a0al.: 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":"19_CR74","doi-asserted-by":"crossref","unstructured":"Yang, W., et al.: Projecting your view attentively: monocular road scene layout estimation via cross-view transformation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15536\u201315545 (2021)","DOI":"10.1109\/CVPR46437.2021.01528"},{"key":"19_CR75","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":"19_CR76","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1007\/978-3-030-58583-9_43","volume-title":"Computer Vision \u2013 ECCV 2020","author":"JH Yoo","year":"2020","unstructured":"Yoo, J.H., Kim, Y., Kim, J., Choi, J.W.: 3D-CVF: generating joint camera and LiDAR features using cross-view spatial feature fusion for 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12372, pp. 720\u2013736. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58583-9_43"},{"key":"19_CR77","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1007\/978-3-031-20077-9_37","volume-title":"ECCV 2022","author":"J Yu","year":"2022","unstructured":"Yu, J., et al.: MTTrans: cross-domain object detection with mean teacher transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 629\u2013645. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_37"},{"key":"19_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, P., Zhang, B., Zhang, T., Chen, D., Wang, Y., Wen, F.: Prototypical pseudo label denoising and target structure learning for domain adaptive semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12414\u201312424 (2021)","DOI":"10.1109\/CVPR46437.2021.01223"},{"key":"19_CR79","unstructured":"Zhang, Q., Zhang, J., Liu, W., Tao, D.: Category anchor-guided unsupervised domain adaptation for semantic segmentation. In: Advances in Neural Information Processing Systems, pp. 433\u2013443 (2019)"},{"key":"19_CR80","unstructured":"Zhang, Y.: A survey of unsupervised domain adaptation for visual recognition. arXiv preprint arXiv:2112.06745 (2021)"},{"key":"19_CR81","unstructured":"Zhang, Y., et al.: BEVerse: unified perception and prediction in birds-eye-view for vision-centric autonomous driving. arXiv preprint arXiv:2205.09743 (2022)"},{"issue":"3","key":"19_CR82","first-page":"348","volume":"52","author":"Q Zhao","year":"2009","unstructured":"Zhao, Q.: A survey on virtual reality. Sci. China Ser. F: Inf. Sci. 52(3), 348\u2013400 (2009)","journal-title":"Sci. China Ser. F: Inf. Sci."},{"key":"19_CR83","doi-asserted-by":"crossref","unstructured":"Zhou, B., Kr\u00e4henb\u00fchl, P.: Cross-view transformers for real-time map-view semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13760\u201313769 (2022)","DOI":"10.1109\/CVPR52688.2022.01339"},{"key":"19_CR84","doi-asserted-by":"crossref","unstructured":"Zhu, J., Bai, H., Wang, L.: Patch-mix transformer for unsupervised domain adaptation: a game perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3561\u20133571 (2023)","DOI":"10.1109\/CVPR52729.2023.00347"},{"key":"19_CR85","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Cylindrical and asymmetrical 3D convolution networks for lidar segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9939\u20139948 (2021)","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"19_CR86","doi-asserted-by":"crossref","unstructured":"Zou, J., et al.: HFT: lifting perspective representations via hybrid feature transformation. arXiv preprint arXiv:2204.05068 (2022)","DOI":"10.1109\/ICRA48891.2023.10161214"},{"key":"19_CR87","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Kumar, B., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 289\u2013305 (2018)","DOI":"10.1007\/978-3-030-01219-9_18"}],"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\/978-3-031-73007-8_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T22:37:36Z","timestamp":1732833456000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73007-8_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,1]]},"ISBN":["9783031730061","9783031730078"],"references-count":87,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73007-8_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,1]]},"assertion":[{"value":"1 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"}}]}}