{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T11:27:10Z","timestamp":1775042830431,"version":"3.50.1"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729720","type":"print"},{"value":"9783031729737","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-72973-7_12","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"197-213","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards Stable 3D Object Detection"],"prefix":"10.1007","author":[{"given":"Jiabao","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guochao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liujiang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qibin","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"12_CR1","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":"12_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the clear mot metrics. EURASIP J. Image Video Process. 2008, 1\u201310 (2008)","journal-title":"EURASIP J. Image Video Process."},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Bewley, A., Ge, Z., Ott, L., Ramos, F., Upcroft, B.: Simple online and realtime tracking. In: 2016 IEEE International Conference on Image Processing (ICIP), pp. 3464\u20133468. IEEE (2016)","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"12_CR4","unstructured":"Bewley, A., Sun, P., Mensink, T., Anguelov, D., Sminchisescu, C.: Range conditioned dilated convolutions for scale invariant 3d object detection. arXiv preprint arXiv:2005.09927 (2020)"},{"issue":"27599\u201323175","key":"12_CR5","first-page":"41","volume":"8","author":"G Bishop","year":"2001","unstructured":"Bishop, G., Welch, G., et al.: An introduction to the kalman filter. Proc. SIGGRAPH Course 8(27599\u201323175), 41 (2001)","journal-title":"Proc. SIGGRAPH Course"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al: nuscenes: a multimodal dataset for autonomous driving. In: CVPR, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Chai, Y., et al.: To the point: efficient 3d object detection in the range image with graph convolution kernels. In: CVPR, pp. 16000\u201316009 (2021)","DOI":"10.1109\/CVPR46437.2021.01574"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Chen, X., Ma, H., Wan, J., Li, B., Xia, T.: Multi-view 3d object detection network for autonomous driving. In: CVPR, pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, S., Shen, X., Jia, J.: Fast point r-cnn. In: ICCV, pp. 9775\u20139784 (2019)","DOI":"10.1109\/ICCV.2019.00987"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Y., Liu, J., Zhang, X., Qi, X., Jia, J.: Voxelnext: fully sparse voxelnet for 3d object detection and tracking. In: CVPR, pp. 21674\u201321683 (2023)","DOI":"10.1109\/CVPR52729.2023.02076"},{"key":"12_CR11","unstructured":"Contributors, M.: MMDetection3D: OpenMMLab next-generation platform for general 3D object detection. https:\/\/github.com\/open-mmlab\/mmdetection3d (2020)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Deng, J., Shi, S., Li, P., Zhou, W., Zhang, Y., Li, H.: Voxel r-cnn: towards high performance voxel-based 3d object detection. In: AAAI, vol.\u00a035, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"12_CR13","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"12_CR14","unstructured":"Everingham, M., Van\u00a0Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html (2005)"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Fan, L., et al.: Embracing single stride 3d object detector with sparse transformer. In: CVPR, pp. 8458\u20138468 (2022)","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Fan, L., Xiong, X., Wang, F., Wang, N., Zhang, Z.: Rangedet: in defense of range view for lidar-based 3d object detection. In: ICCV, pp. 2918\u20132927 (2021)","DOI":"10.1109\/ICCV48922.2021.00291"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: CVPR, pp. 3354\u20133361 (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Lang, A.H., Vora, S., Caesar, H., Zhou, L., Yang, J., Beijbom, O.: Pointpillars: fast encoders for object detection from point clouds. In: CVPR, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Li, J., Luo, C., Yang, X.: Pillarnext: rethinking network designs for 3d object detection in lidar point clouds. In: CVPR, pp. 17567\u201317576 (2023)","DOI":"10.1109\/CVPR52729.2023.01685"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, F., Wang, N.: Lidar r-cnn: an efficient and universal 3d object detector. In: CVPR, pp. 7546\u20137555 (2021)","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Bevformer: learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. In: ECCV, pp. 1\u201318. Springer (2022)","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Bevfusion: multi-task multi-sensor fusion with unified bird\u2019s-eye view representation. In: IEEE International Conference on Robotics and Automation, pp. 2774\u20132781. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160968"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yang, X., Tang, H., Yang, S., Han, S.: Flatformer: flattened window attention for efficient point cloud transformer. In: CVPR, pp. 1200\u20131211 (2023)","DOI":"10.1109\/CVPR52729.2023.00122"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Meyer, G.P., Laddha, A., Kee, E., Vallespi-Gonzalez, C., Wellington, C.K.: Lasernet: an efficient probabilistic 3d object detector for autonomous driving. In: CVPR, pp. 12677\u201312686 (2019)","DOI":"10.1109\/CVPR.2019.01296"},{"key":"12_CR25","unstructured":"Pang, Z., Li, Z., Wang, N.: Simpletrack: Understanding and rethinking 3d multi-object tracking. arXiv preprint arXiv:2111.09621 (2021)"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Prakash, A., Chitta, K., Geiger, A.: Multi-modal fusion transformer for end-to-end autonomous driving. In: CVPR, pp. 7077\u20137087 (2021)","DOI":"10.1109\/CVPR46437.2021.00700"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Litany, O., He, K., Guibas, L.J.: Deep hough voting for 3d object detection in point clouds. In: ICCV, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Qi, C.R., Liu, W., Wu, C., Su, H., Guibas, L.J.: Frustum pointnets for 3d object detection from rgb-d data. In: CVPR, pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: Pv-rcnn: point-voxel feature set abstraction for 3d object detection. In: CVPR, pp. 10529\u201310538 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Shi, S., Jiang, L., Deng, J., Wang, Z., Guo, C., Shi, J., Wang, X., Li, H.: Pv-rcnn++: Point-voxel feature set abstraction with local vector representation for 3d object detection. arXiv preprint arXiv:2102.00463 (2021)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. In: CVPR, pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"issue":"8","key":"12_CR32","first-page":"2647","volume":"43","author":"S Shi","year":"2020","unstructured":"Shi, S., Wang, Z., Shi, J., Wang, X., Li, H.: From points to parts: 3d object detection from point cloud with part-aware and part-aggregation network. IEEE TPAMI 43(8), 2647\u20132664 (2020)","journal-title":"IEEE TPAMI"},{"key":"12_CR33","unstructured":"Shi, S., Wang, Z., Wang, X., Li, H.: Part-a$$\\hat{\\,\\,}$$ 2 net: 3d part-aware and aggregation neural network for object detection from point cloud. arXiv preprint arXiv:1907.036702(3) (2019)"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Shi, W., Rajkumar, R.: Point-GNN: graph neural network for 3d object detection in a point cloud. In: CVPR, pp. 1711\u20131719 (2020)","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"12_CR35","unstructured":"Sun, P., et\u00a0al.: Scalability in perception for autonomous driving: waymo open dataset. In: CVPR, pp. 2446\u20132454 (2020)"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: RSN: range sparse net for efficient, accurate lidar 3d object detection. In: CVPR, pp. 5725\u20135734 (2021)","DOI":"10.1109\/CVPR46437.2021.00567"},{"key":"12_CR37","unstructured":"Team, O.D.: Openpcdet: An open-source toolbox for 3d object detection from point clouds. https:\/\/github.com\/open-mmlab\/OpenPCDet (2020)"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Wang, H., et al.: DSVT: dynamic sparse voxel transformer with rotated sets. In: CVPR, pp. 13520\u201313529 (2023)","DOI":"10.1109\/CVPR52729.2023.01299"},{"key":"12_CR39","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)"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Weng, X., Wang, J., Held, D., Kitani, K.: 3D multi-object tracking: a baseline and new evaluation metrics. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 10359\u201310366. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341164"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: 2017 IEEE international conference on image processing (ICIP), pp. 3645\u20133649. IEEE (2017)","DOI":"10.1109\/ICIP.2017.8296962"},{"issue":"10","key":"12_CR42","doi-asserted-by":"publisher","first-page":"3337","DOI":"10.3390\/s18103337","volume":"18","author":"Y Yan","year":"2018","unstructured":"Yan, Y., Mao, Y., Li, B.: Second: sparsely embedded convolutional detection. Sensors 18(10), 3337 (2018)","journal-title":"Sensors"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3DSSD: point-based 3D single stage object detector. In: CVPR, pp. 11040\u201311048 (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: Ipod: Intensive point-based object detector for point cloud. arXiv preprint arXiv:1812.05276 (2018)","DOI":"10.1109\/ICCV.2019.00204"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Yin, T., Zhou, X., Krahenbuhl, P.: Center-based 3D object detection and tracking. In: CVPR, pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: Varifocalnet: an IoU-aware dense object detector. In: CVPR, pp. 8514\u20138523 (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"12_CR47","unstructured":"Zhang, H., Wang, N.: On the stability of video detection and tracking. arXiv preprint arXiv:1611.06467 (2016)"},{"key":"12_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Hu, Q., Xu, G., Ma, Y., Wan, J., Guo, Y.: Not all points are equal: learning highly efficient point-based detectors for 3D lidar point clouds. In: CVPR, pp. 18953\u201318962 (2022)","DOI":"10.1109\/CVPR52688.2022.01838"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: VoxelNet: end-to-end learning for point cloud based 3D object detection. In: CVPR, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Zhao, X., Wang, Y., Wang, P., Foroosh, H.: Centerformer: center-based transformer for 3D object detection. In: European Conference on Computer Vision, pp. 496\u2013513. Springer (2022)","DOI":"10.1007\/978-3-031-19839-7_29"}],"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\/978-3-031-72973-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,15]],"date-time":"2025-02-15T15:00:46Z","timestamp":1739631646000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72973-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031729720","9783031729737"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72973-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}