{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T13:29:33Z","timestamp":1780925373470,"version":"3.54.1"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200762","type":"print"},{"value":"9783031200779","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20077-9_32","type":"book-chapter","created":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T16:21:52Z","timestamp":1667665312000},"page":"544-561","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Rethinking IoU-based Optimization for\u00a0Single-stage 3D Object Detection"],"prefix":"10.1007","author":[{"given":"Hualian","family":"Sheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sijia","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xian-Sheng","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min-Jian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gim Hee","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,6]]},"reference":[{"key":"32_CR1","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1907\u20131915 (2017)","DOI":"10.1109\/CVPR.2017.691"},{"key":"32_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1007\/978-3-030-58558-7_12","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Chen","year":"2020","unstructured":"Chen, Z., et al.: PIoU loss: towards accurate oriented object detection in complex environments. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 195\u2013211. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_12"},{"key":"32_CR3","unstructured":"Contributors, M.: MMDetection3D: OpenMMLab next-generation platform for general 3D object detection. https:\/\/github.com\/open-mmlab\/mmdetection3d (2020)"},{"key":"32_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. arXiv preprint arXiv:2012.15712 (2020)","DOI":"10.1609\/aaai.v35i2.16207"},{"issue":"11","key":"32_CR5","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the kitti dataset. Int. J. Rob. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Rob. Res."},{"key":"32_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Graham, B.: Sparse 3D convolutional neural networks. arXiv preprint arXiv:1505.02890 (2015)","DOI":"10.5244\/C.29.150"},{"key":"32_CR8","doi-asserted-by":"crossref","unstructured":"Graham, B., van der Maaten, L.: Submanifold sparse convolutional networks. arXiv preprint arXiv:1706.01307 (2017)","DOI":"10.1109\/CVPR.2018.00961"},{"key":"32_CR9","doi-asserted-by":"crossref","unstructured":"He, C., Zeng, H., Huang, J., Hua, X.S., Zhang, L.: Structure aware single-stage 3D object detection from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11873\u201311882 (2020)","DOI":"10.1109\/CVPR42600.2020.01189"},{"key":"32_CR10","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 (CVPR), pp. 12697\u201312705 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Li, J., Tang, J., Yang, J.: Generalized focal loss v2: learning reliable localization quality estimation for dense object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11632\u201311641 (2021)","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"32_CR12","first-page":"21002","volume":"33","author":"X Li","year":"2020","unstructured":"Li, X., et al.: Generalized focal loss: learning qualified and distributed bounding boxes for dense object detection. Adv. Neural Inf. Process. Syst. (NIPS) 33, 21002\u201321012 (2020)","journal-title":"Adv. Neural Inf. Process. Syst. (NIPS)"},{"key":"32_CR13","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, F., Wang, N.: Lidar r-cnn: an efficient and universal 3D object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7546\u20137555 (2021)","DOI":"10.1109\/CVPR46437.2021.00746"},{"key":"32_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"32_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. arXiv preprint arXiv:2103.14030 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"32_CR16","doi-asserted-by":"crossref","unstructured":"Mao, J., et al.: Voxel transformer for 3D object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3164\u20133173 (2021)","DOI":"10.1109\/ICCV48922.2021.00315"},{"key":"32_CR17","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 918\u2013927 (2018)","DOI":"10.1109\/CVPR.2018.00102"},{"key":"32_CR18","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 652\u2013660 (2017)"},{"key":"32_CR19","first-page":"5099","volume":"30","author":"CR Qi","year":"2017","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. Adv. Neural Inf. Process. Syst. (NIPS) 30, 5099\u20135108 (2017)","journal-title":"Adv. Neural Inf. Process. Syst. (NIPS)"},{"key":"32_CR20","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"32_CR21","doi-asserted-by":"crossref","unstructured":"Sheng, H., et al.: Improving 3D object detection with channel-wise transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2743\u20132752 (2021)","DOI":"10.1109\/ICCV48922.2021.00274"},{"key":"32_CR22","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: Pv-rcnn: point-voxel feature set abstraction for 3D object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10529\u201310538 (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"32_CR23","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 (CVPR), pp. 770\u2013779 (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"32_CR24","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 Trans. Pattern Anal. Mach. Intell. (TPAMI) 43, 2647\u20132664 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"32_CR25","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 (CVPR), pp. 1711\u20131719 (2020)","DOI":"10.1109\/CVPR42600.2020.00178"},{"key":"32_CR26","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"32_CR27","unstructured":"Team, O.D.: Openpcdet: an open-source toolbox for 3D object detection from point clouds (2020). https:\/\/github.com\/open-mmlab\/OpenPCDet"},{"key":"32_CR28","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. (NIPS), 5998\u20136008 (2017)"},{"key":"32_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Pillar-based object detection for autonomous driving. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 18\u201334 (2020)","DOI":"10.1007\/978-3-030-58542-6_2"},{"key":"32_CR30","doi-asserted-by":"crossref","unstructured":"Xu, Q., Zhong, Y., Neumann, U.: Behind the curtain: learning occluded shapes for 3D object detection. arXiv preprint arXiv:2112.02205 (2021)","DOI":"10.1609\/aaai.v36i3.20194"},{"issue":"10","key":"32_CR31","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":"32_CR32","unstructured":"Yang, X., Yan, J., Ming, Q., Wang, W., Zhang, X., Tian, Q.: Rethinking rotated object detection with gaussian wasserstein distance loss. arXiv preprint arXiv:2101.11952 (2021)"},{"key":"32_CR33","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: Scrdet: towards more robust detection for small, cluttered and rotated objects. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 8232\u20138241 (2019)","DOI":"10.1109\/ICCV.2019.00832"},{"key":"32_CR34","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Jia, J.: 3DSSD: point-based 3D single stage object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11040\u201311048 (2020)","DOI":"10.1109\/CVPR42600.2020.01105"},{"key":"32_CR35","doi-asserted-by":"crossref","unstructured":"Yang, Z., Sun, Y., Liu, S., Shen, X., Jia, J.: Std: sparse-to-dense 3D object detector for point cloud. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1951\u20131960 (2019)","DOI":"10.1109\/ICCV.2019.00204"},{"key":"32_CR36","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 (CVPR), pp. 11784\u201311793 (2021)","DOI":"10.1109\/CVPR46437.2021.01161"},{"key":"32_CR37","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Chen, S., Jiang, L., Fu, C.W.: Cia-ssd: confident iou-aware single-stage object detector from point cloud. arXiv preprint arXiv:2012.03015 (2020)","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"32_CR38","doi-asserted-by":"crossref","unstructured":"Zheng, W., Tang, W., Jiang, L., Fu, C.W.: SE-SSD: self-ensembling single-stage object detector from point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14494\u201314503 (2021)","DOI":"10.1109\/CVPR46437.2021.01426"},{"key":"32_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1007\/978-3-030-58565-5_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Yu Zheng","year":"2020","unstructured":"Zheng, Yu., Zhang, D., Xie, S., Lu, J., Zhou, J.: Rotation-robust intersection over union for 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 464\u2013480. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_28"},{"key":"32_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-iou loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 34, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"32_CR41","doi-asserted-by":"crossref","unstructured":"Zhou, D., et al.: Iou loss for 2D\/3D object detection. In: International Conference on 3D Vision (3DV), pp. 85\u201394. IEEE (2019)","DOI":"10.1109\/3DV.2019.00019"},{"key":"32_CR42","unstructured":"Zhou, Y., et al.: End-to-end multi-view fusion for 3D object detection in lidar point clouds. In: Conference on Robot Learning (CoRL), pp. 923\u2013932 (2020)"},{"key":"32_CR43","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\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4490\u20134499 (2018)","DOI":"10.1109\/CVPR.2018.00472"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20077-9_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:17:40Z","timestamp":1667866660000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20077-9_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200762","9783031200779"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20077-9_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"6 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}