{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T16:30:28Z","timestamp":1778603428797,"version":"3.51.4"},"publisher-location":"Cham","reference-count":77,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031734106","type":"print"},{"value":"9783031734113","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T00:00:00Z","timestamp":1732320000000},"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\/978-3-031-73411-3_16","type":"book-chapter","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T20:09:09Z","timestamp":1732306149000},"page":"273-292","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9756-4488","authenticated-orcid":false,"given":"Chunliang","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2358-6969","authenticated-orcid":false,"given":"Wencheng","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1127-3686","authenticated-orcid":false,"given":"Junbo","family":"Yin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9386-9677","authenticated-orcid":false,"given":"Sanyuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1883-2086","authenticated-orcid":false,"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,23]]},"reference":[{"key":"16_CR1","unstructured":"Mobileye at CES 2024. https:\/\/www.mobileye.com\/ces-2024\/"},{"key":"16_CR2","unstructured":"NVIDIA DRIVE Solutions. https:\/\/developer.nvidia.com\/drive"},{"key":"16_CR3","doi-asserted-by":"publisher","unstructured":"Bai, Y., Chen, Z., Fu, Z., Peng, L., Liang, P., Cheng, E.: CurveFormer: 3D lane detection by curve propagation with curve queries and attention. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 7062\u20137068 (2023). https:\/\/doi.org\/10.1109\/ICRA48891.2023.10161160","DOI":"10.1109\/ICRA48891.2023.10161160"},{"key":"16_CR4","doi-asserted-by":"publisher","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11618\u201311628. IEEE, Seattle, WA, USA (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01164","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"16_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"16_CR6","doi-asserted-by":"publisher","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.) Computer Vision \u2013 ECCV 2022, vol. 13698, pp. 550\u2013567. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_32","DOI":"10.1007\/978-3-031-19839-7_32"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Chen, X., Kundu, K., Zhang, Z., Ma, H., Fidler, S., Urtasun, R.: Monocular 3D object detection for autonomous driving. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2147\u20132156 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"16_CR8","unstructured":"Chen, Z., Badrinarayanan, V., Lee, C.Y., Rabinovich, A.: GradNorm: gradient normalization for adaptive loss balancing in deep multitask networks. In: Proceedings of the 35th International Conference on Machine Learning, pp. 794\u2013803. PMLR (2018)"},{"key":"16_CR9","unstructured":"Cheng, W., Yin, J., Li, W., Yang, R., Shen, J.: Language-guided 3D object detection in point cloud for autonomous driving (2023)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Feng, Z., Guo, S., Tan, X., Xu, K., Wang, M., Ma, L.: Rethinking efficient lane detection via curve modeling. arXiv preprint arXiv:2203.02431 (2023)","DOI":"10.1109\/CVPR52688.2022.01655"},{"key":"16_CR11","doi-asserted-by":"publisher","unstructured":"Garnett, N., Cohen, R., Pe\u2019er, T., Lahav, R., Levi, D.: 3D-LaneNet: End-to-end 3D multiple lane detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2921\u20132930. IEEE, Seoul, Korea (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00301","DOI":"10.1109\/ICCV.2019.00301"},{"key":"16_CR12","doi-asserted-by":"publisher","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3354\u20133361 (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6248074","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"16_CR13","unstructured":"Guo, P., Lee, C.Y., Ulbricht, D.: Learning to branch for multi-task learning. In: Proceedings of the 37th International Conference on Machine Learning, pp. 3854\u20133863. PMLR (2020)"},{"key":"16_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1007\/978-3-030-58589-1_40","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Guo","year":"2020","unstructured":"Guo, Y., et al.: Gen-LaneNet: a generalized and scalable approach for 3D lane detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 666\u2013681. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58589-1_40"},{"key":"16_CR15","unstructured":"Han, W., Shen, J.: Decoupling the curve modeling and pavement regression for lane detection (2023)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16_CR17","unstructured":"Huang, J., Huang, G.: BEVDet4D: exploit temporal cues in multi-camera 3D object detection (2022)"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Anchor3DLane: learning to regress 3D anchors for monocular 3D lane detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognitio, pp. 17451\u201317460 (2023)","DOI":"10.1109\/CVPR52729.2023.01674"},{"key":"16_CR19","doi-asserted-by":"publisher","unstructured":"Huang, Z., et al.: FULLER: unified multi-modality multi-task 3D perception via multi-level gradient calibration. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3479\u20133488. IEEE, Paris, France (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.00324","DOI":"10.1109\/ICCV51070.2023.00324"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Kehl, W., Manhardt, F., Tombari, F., Ilic, S., Navab, N.: SSD-6D: making RGB-based 3D detection and 6D pose estimation great again. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1521\u20131529 (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7482\u20137491 (2018)","DOI":"10.1109\/CVPR.2018.00781"},{"key":"16_CR22","doi-asserted-by":"crossref","unstructured":"Ku, J., Pon, A.D., Waslander, S.L.: Monocular 3D object detection leveraging accurate proposals and shape reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11867\u201311876 (2019)","DOI":"10.1109\/CVPR.2019.01214"},{"issue":"1\u20132","key":"16_CR23","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logistics Q. 2(1\u20132), 83\u201397 (1955). https:\/\/doi.org\/10.1002\/nav.3800020109","journal-title":"Naval Res. Logistics Q."},{"key":"16_CR24","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: a simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Li, X., Yin, J., Li, W., Xu, C., Yang, R., Shen, J.: DI-V2X: learning domain-invariant representation for vehicle-infrastructure collaborative 3D object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a038, pp. 3208\u20133215 (2024)","DOI":"10.1609\/aaai.v38i4.28105"},{"key":"16_CR26","doi-asserted-by":"publisher","unstructured":"Li, X., Yin, J., Shi, B., Li, Y., Yang, R., Shen, J.: LWSIS: LiDAR-guided weakly supervised instance segmentation for autonomous driving. Proc. AAAI Conf. Artif. Intell. 37(2), 1433\u20131441 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i2.25228","DOI":"10.1609\/aaai.v37i2.25228"},{"key":"16_CR27","first-page":"18442","volume":"35","author":"Y Li","year":"2022","unstructured":"Li, Y., Chen, Y., Qi, X., Li, Z., Sun, J., Jia, J.: Unifying Voxel-based representation with transformer for 3D object detection. Adv. Neural. Inf. Process. Syst. 35, 18442\u201318455 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR28","doi-asserted-by":"publisher","unstructured":"Li, Z., et al.: BEVFormer: learning bird\u2019s-eye-view representation from\u00a0multi-camera images via\u00a0spatiotemporal transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022, pp. 1\u201318. LNCS, Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_1","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Liang, M., Yang, B., Chen, Y., Hu, R., Urtasun, R.: 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 (2019)","DOI":"10.1109\/CVPR.2019.00752"},{"key":"16_CR30","first-page":"10421","volume":"35","author":"T Liang","year":"2022","unstructured":"Liang, T., et al.: BEVFusion: a simple and robust LiDAR-camera fusion framework. Adv. Neural. Inf. Process. Syst. 35, 10421\u201310434 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"16_CR32","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"16_CR33","unstructured":"Liu, L., et al.: Towards impartial multi-task learning. In: International Conference on Learning Representations (2020)"},{"issue":"2","key":"16_CR34","doi-asserted-by":"publisher","first-page":"1765","DOI":"10.1609\/aaai.v36i2.20069","volume":"36","author":"R Liu","year":"2022","unstructured":"Liu, R., Chen, D., Liu, T., Xiong, Z., Yuan, Z.: Learning to predict 3D lane shape and camera pose from a single image via geometry constraints. Proc. AAAI Conf. Artif. Intell. 36(2), 1765\u20131772 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i2.20069","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Liu, S., Johns, E., Davison, A.J.: End-to-end multi-task learning with attention. arXiv preprint arXiv:1803.10704 (2019)","DOI":"10.1109\/CVPR.2019.00197"},{"key":"16_CR36","unstructured":"Liu, S., et al.: DAB-DETR: dynamic anchor boxes are better queries for DETR (2022)"},{"key":"16_CR37","doi-asserted-by":"publisher","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.) Computer Vision \u2013 ECCV 2022, vol. 13687, pp. 531\u2013548. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19812-0_31","DOI":"10.1007\/978-3-031-19812-0_31"},{"key":"16_CR38","unstructured":"Liu, Y., et al.: PETRv2: a unified framework for 3D perception from multi-camera images"},{"key":"16_CR39","doi-asserted-by":"publisher","unstructured":"Liu, Z., et al.: BEVFusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 2774\u20132781 (2023). https:\/\/doi.org\/10.1109\/ICRA48891.2023.10160968","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"16_CR40","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: International Conference on Learning Representations (2016)"},{"key":"16_CR41","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2019)"},{"key":"16_CR42","doi-asserted-by":"crossref","unstructured":"Luo, Y., et al.: LATR: 3D lane detection from monocular images with transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7941\u20137952 (2023)","DOI":"10.1109\/ICCV51070.2023.00730"},{"key":"16_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1007\/978-3-030-68238-5_43","volume-title":"Computer Vision \u2013 ECCV 2020 Workshops","author":"Z Ma","year":"2020","unstructured":"Ma, Z., Wang, L., Zhang, H., Lu, W., Yin, J.: RPT: learning point set representation for Siamese visual tracking. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12539, pp. 653\u2013665. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-68238-5_43"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Misra, I., Shrivastava, A., Gupta, A., Hebert, M.: Cross-stitch networks for multi-task learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3994\u20134003 (2016)","DOI":"10.1109\/CVPR.2016.433"},{"key":"16_CR45","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":"16_CR46","unstructured":"Navon, A., et al.: Multi-task learning as a bargaining game (2022)"},{"key":"16_CR47","unstructured":"Neven, D., De\u00a0Brabandere, B., Georgoulis, S., Proesmans, M., Van\u00a0Gool, L.: Fast scene understanding for autonomous driving. arXiv preprint arXiv:1708.02550 (2017)"},{"key":"16_CR48","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-030-58568-6_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Philion","year":"2020","unstructured":"Philion, J., Fidler, S.: Lift, splat, shoot: encoding images from arbitrary camera rigs by implicitly unprojecting to 3D. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 194\u2013210. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_12"},{"key":"16_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":"16_CR50","unstructured":"Roddick, T., Kendall, A., Cipolla, R.: Orthographic feature transform for monocular 3D object detection. arXiv preprint arXiv:1811.08188 (2018)"},{"issue":"01","key":"16_CR51","doi-asserted-by":"publisher","first-page":"4822","DOI":"10.1609\/aaai.v33i01.33014822","volume":"33","author":"S Ruder","year":"2019","unstructured":"Ruder, S., Bingel, J., Augenstein, I., S\u00f8gaard, A.: Latent multi-task architecture learning. Proc. AAAI Conf. Artif. Intell. 33(01), 4822\u20134829 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33014822","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"16_CR52","unstructured":"Sener, O., Koltun, V.: Multi-task learning as multi-objective optimization. In: Advances in Neural Information Processing Systems, vol.\u00a031. Curran Associates, Inc. (2018)"},{"key":"16_CR53","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: scalability in perception for autonomous driving: Waymo open dataset. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"16_CR54","doi-asserted-by":"publisher","unstructured":"Teichmann, M., Weber, M., Z\u00f6llner, M., Cipolla, R., Urtasun, R.: MultiNet: real-time joint semantic reasoning for autonomous driving. In: 2018 IEEE Intelligent Vehicles Symposium (IV), pp. 1013\u20131020 (2018). https:\/\/doi.org\/10.1109\/IVS.2018.8500504","DOI":"10.1109\/IVS.2018.8500504"},{"issue":"7","key":"16_CR55","doi-asserted-by":"publisher","first-page":"3614","DOI":"10.1109\/TPAMI.2021.3054719","volume":"44","author":"S Vandenhende","year":"2022","unstructured":"Vandenhende, S., Georgoulis, S., Van Gansbeke, W., Proesmans, M., Dai, D., Van Gool, L.: Multi-task learning for dense prediction tasks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(7), 3614\u20133633 (2022). https:\/\/doi.org\/10.1109\/TPAMI.2021.3054719","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR56","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol.\u00a030. Curran Associates, Inc. (2017)"},{"key":"16_CR57","doi-asserted-by":"crossref","unstructured":"Wang, R., Qin, J., Li, K., Li, Y., Cao, D., Xu, J.: BEV-LaneDet: an efficient 3D lane detection based on virtual camera via key-points. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1002\u20131011 (2023)","DOI":"10.1109\/CVPR52729.2023.00103"},{"key":"16_CR58","doi-asserted-by":"crossref","unstructured":"Wang, S., Liu, Y., Wang, T., Li, Y., Zhang, X.: Exploring object-centric temporal modeling for efficient multi-view 3D object detection (2023)","DOI":"10.1109\/ICCV51070.2023.00335"},{"key":"16_CR59","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":"16_CR60","doi-asserted-by":"publisher","unstructured":"Wang, Y., Yin, J., Li, W., Frossard, P., Yang, R., Shen, J.: SSDA3D: semi-supervised domain adaptation for 3D object detection from point cloud. Proc. AAAI Conf. Artif. Intell. 37(3), 2707\u20132715 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i3.25370","DOI":"10.1609\/aaai.v37i3.25370"},{"issue":"3","key":"16_CR61","doi-asserted-by":"publisher","first-page":"2567","DOI":"10.1609\/aaai.v36i3.20158","volume":"36","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor DETR: query design for transformer-based detector. Proc. AAAI Conf. Artif. Intell. 36(3), 2567\u20132575 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i3.20158","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"16_CR62","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: Proceedings of the 5th Conference on Robot Learning, pp. 180\u2013191. PMLR (2022)"},{"key":"16_CR63","unstructured":"Wu, D., Chang, J., Jia, F., Liu, Y., Wang, T., Shen, J.: TopoMLP: an simple yet strong pipeline for driving topology reasoning. arXiv preprint arXiv:2310.06753 (2023)"},{"key":"16_CR64","unstructured":"Wu, D., et al.: The 1st-place solution for CVPR 2023 OpenLane topology in autonomous driving challenge. arXiv preprint arXiv:2306.09590 (2023)"},{"key":"16_CR65","unstructured":"Xie, E., et al.: M\\$$$\\hat{\\,}$$2\\$BEV: multi-camera joint 3D detection and segmentation with unified birds-eye view representation. arXiv preprint arXiv:2204.05088 (2022)"},{"key":"16_CR66","doi-asserted-by":"crossref","unstructured":"Xu, D., Ouyang, W., Wang, X., Sebe, N.: PAD-Net: multi-tasks guided prediction-and-distillation network for simultaneous depth estimation and scene parsing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 675\u2013684 (2018)","DOI":"10.1109\/CVPR.2018.00077"},{"key":"16_CR67","doi-asserted-by":"crossref","unstructured":"Yan, F., et al.: ONCE-3DLanes: building monocular 3D lane detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17143\u201317152 (2022)","DOI":"10.1109\/CVPR52688.2022.01663"},{"key":"16_CR68","doi-asserted-by":"publisher","unstructured":"Yang, Z., Liu, S., Hu, H., Wang, L., Lin, S.: RepPoints: point set representation for object detection. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 9656\u20139665. IEEE, Seoul, South Korea (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00975","DOI":"10.1109\/ICCV.2019.00975"},{"key":"16_CR69","unstructured":"Yao, C., Yu, L., Wu, Y., Jia, Y.: Sparse point guided 3D lane detection"},{"key":"16_CR70","doi-asserted-by":"publisher","unstructured":"Yin, J., et al.: Semi-supervised 3D object detection with proficient teachers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022, vol. 13698, pp. 727\u2013743. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19839-7_42","DOI":"10.1007\/978-3-031-19839-7_42"},{"key":"16_CR71","doi-asserted-by":"crossref","unstructured":"Yin, J., Shen, J., Chen, R., Li, W., Yang, R., Frossard, P., Wang, W.: IS-Fusion: instance-scene collaborative fusion for multimodal 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14905\u201314915 (2024)","DOI":"10.1109\/CVPR52733.2024.01412"},{"key":"16_CR72","doi-asserted-by":"crossref","unstructured":"Yin, J., Wang, W., Meng, Q., Yang, R., Shen, J.: A unified object motion and affinity model for online multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6768\u20136777 (2020)","DOI":"10.1109\/CVPR42600.2020.00680"},{"key":"16_CR73","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. arXiv preprint arXiv:2001.06782 (2020)"},{"issue":"11","key":"16_CR74","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., Liu, W.: FairMOT: on the fairness of detection and re-identification in multiple object tracking. Int. J. Comput. Vis. 129(11), 3069\u20133087 (2021). https:\/\/doi.org\/10.1007\/s11263-021-01513-4","journal-title":"Int. J. Comput. Vis."},{"key":"16_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, D., et al.: Joint 3D instance segmentation and object detection for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1839\u20131849 (2020)","DOI":"10.1109\/CVPR42600.2020.00191"},{"key":"16_CR76","doi-asserted-by":"crossref","unstructured":"Zhou, D., et al.: IAFA: instance-aware feature aggregation for 3D object detection from a single image. In: Proceedings of the Asian Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-69525-5_25"},{"key":"16_CR77","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2021)"}],"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\/978-3-031-73411-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T21:26:35Z","timestamp":1732310795000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73411-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,23]]},"ISBN":["9783031734106","9783031734113"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73411-3_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,23]]},"assertion":[{"value":"23 November 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"}}]}}