{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:14:39Z","timestamp":1757618079383,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031917660"},{"type":"electronic","value":"9783031917677"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-91767-7_6","type":"book-chapter","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T13:44:08Z","timestamp":1748267048000},"page":"80-96","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["3D Object Detection and\u00a0Tracking Refinement with\u00a0Ensemble Methods and\u00a0Spatiotemporal Filtering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5274-3693","authenticated-orcid":false,"given":"Sandesh","family":"Jain","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4119-8239","authenticated-orcid":false,"given":"Surendrabikram","family":"Thapa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sanjana","family":"Bharadwaj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhijit","family":"Sarkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"A. Lynn","family":"Abbott","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Xuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"6_CR1","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":"6_CR2","unstructured":"Chen, J., Fang, P., Lin, Z., Zeng, D., Liu, W.: Rethinking the competition between detection and reid in multiobject tracking. IEEE Trans. Pattern Anal. Mach. Intell. (2022)"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chen, R., et al.: Clip2scene: towards label-efficient 3d scene understanding by clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7020\u20137030 (2023)","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"6_CR4","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1201\u20131209 (2021)","DOI":"10.1609\/aaai.v35i2.16207"},{"key":"6_CR5","unstructured":"Fang, P., Sun, Y., Lin, Z., Zeng, D., Liu, W.: Simpletrack: understanding and rethinking 3d multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10189\u201310198 (2021)"},{"key":"6_CR6","doi-asserted-by":"crossref","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. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"6_CR7","unstructured":"Guo, X., Li, H., Li, S., Liu, Y.: 3d object recognition with ensemble learning\u2013a study of point cloud-based deep learning models, pp. 3423\u20133429 (2020)"},{"key":"6_CR8","unstructured":"He, K., Sun, J., Cao, Y., Zhou, X.: Weighted boxes fusion: ensembling boxes from different object detection models, pp. 8849\u20138858 (2019)"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Hegde, D., Valanarasu, J.M.J., Patel, V.: Clip goes 3d: leveraging prompt tuning for language grounded 3d recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2028\u20132038 (2023)","DOI":"10.1109\/ICCVW60793.2023.00217"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Jain, S., Thapa, S., Chen, K.T., Abbott, A.L., Sarkar, A.: Semantic understanding of traffic scenes with large vision language models. In: 2024 IEEE Intelligent Vehicles Symposium (IV), pp. 1580\u20131587 (2024)","DOI":"10.1109\/IV55156.2024.10588373"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Kim, A., O\u0161ep, A., Leal-Taix\u00e9, L.: Eagermot: 3d multi-object tracking via sensor fusion. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 11315\u201311321. IEEE (2021)","DOI":"10.1109\/ICRA48506.2021.9562072"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Koguciuk, D., Chechli\u0144ski, \u0141., El-Gaaly, T.: 3d object recognition with ensemble learning-a study of point cloud-based deep learning models. In: International Symposium on Visual Computing, pp. 100\u2013114. Springer (2019)","DOI":"10.1007\/978-3-030-33723-0_9"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Koh, J., Kim, J., Yoo, J.H., Kim, Y., Kum, D., Choi, J.W.: Joint 3d object detection and tracking using spatio-temporal representation of camera image and lidar point clouds. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 1210\u20131218 (2022)","DOI":"10.1609\/aaai.v36i1.20007"},{"key":"6_CR14","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Li, Q., Li, R., Ji, K., Dai, W.: Kalman filter and its application. In: 2015 8th International Conference on Intelligent Networks and Intelligent Systems (ICINIS), pp. 74\u201377. IEEE (2015)","DOI":"10.1109\/ICINIS.2015.35"},{"key":"6_CR16","unstructured":"Li, Y., Liu, X., Zhao, X., Li, X., Zhu, X.: Learnable online graph representations for3d multi-object tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9723\u20139732 (2020)"},{"key":"6_CR17","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":"6_CR18","doi-asserted-by":"crossref","unstructured":"Liu, W., Song, D., Wang, Z., Fang, K.: Error overboundings of kf-based imu\/gnss integrated system against imu faults. Sensors (Basel, Switzerland) 19(22) (2019)","DOI":"10.3390\/s19224912"},{"key":"6_CR19","unstructured":"Luo, W., Zhao, X., Kim, T.K.: Multiple object tracking: a review. arXiv preprint arXiv:1409.7618, 1(1), 1 (2014)"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Pang, Z., Li, Z., Wang, N.: Simpletrack: understanding and rethinking 3d multi-object tracking. In: European Conference on Computer Vision, pp. 680\u2013696. Springer (2022)","DOI":"10.1007\/978-3-031-25056-9_43"},{"key":"6_CR21","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3d classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: Pointrcnn: 3d object proposal generation and detection from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Shi, W., Rajkumar, R.: Point-gnn: graph neural network for 3d object detection in a point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1711\u20131719 (2020)","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Tu, J., Wang, P., Liu, F.: Pp-rcnn: point-pillars feature set abstraction for 3d real-time object detection. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20138. IEEE (2021)","DOI":"10.1109\/IJCNN52387.2021.9534098"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Weng, X., Wang, J., Held, D., Kitani, K.: Ab3dmot: a baseline for 3d multi-object tracking and new evaluation metrics. arXiv preprint arXiv:2008.08063 (2020)","DOI":"10.1109\/IROS45743.2020.9341164"},{"issue":"2","key":"6_CR26","doi-asserted-by":"publisher","first-page":"1152","DOI":"10.1109\/JSEN.2020.3020626","volume":"21","author":"Y Wu","year":"2020","unstructured":"Wu, Y., Wang, Y., Zhang, S., Ogai, H.: Deep 3d object detection networks using lidar data: a review. IEEE Sens. J. 21(2), 1152\u20131171 (2020)","journal-title":"IEEE Sens. J."},{"key":"6_CR27","unstructured":"Xu, B., Li, J., Sun, X., Zhao, H., Zeng, S.: Sess: self-ensembling semi-supervised 3d object detection, pp. 8854\u20138863 (2021)"},{"key":"6_CR28","doi-asserted-by":"crossref","unstructured":"Xu, Q., Sun, X., Wu, C.Y., Wang, P., Neumann, U.: Grid-gcn for fast and scalable point cloud learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5661\u20135670 (2020)","DOI":"10.1109\/CVPR42600.2020.00570"},{"key":"6_CR29","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":"6_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Tuzel, O.: Voxelnet: end-to-end learning for point cloud based 3d object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"},{"issue":"10","key":"6_CR31","doi-asserted-by":"publisher","first-page":"6807","DOI":"10.1109\/TPAMI.2021.3098789","volume":"44","author":"X Zhu","year":"2021","unstructured":"Zhu, X., et al.: Cylindrical and asymmetrical 3d convolution networks for lidar-based perception. IEEE Trans. Pattern Anal. Mach. Intell. 44(10), 6807\u20136822 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-91767-7_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T15:41:20Z","timestamp":1757173280000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-91767-7_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031917660","9783031917677"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-91767-7_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","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"}}]}}