{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T15:33:52Z","timestamp":1773156832238,"version":"3.50.1"},"publisher-location":"Cham","reference-count":54,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585648","type":"print"},{"value":"9783030585655","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58565-5_28","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T12:03:19Z","timestamp":1605096199000},"page":"464-480","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Rotation-Robust Intersection over Union for 3D Object Detection"],"prefix":"10.1007","author":[{"given":"Yu","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Danyang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Sinan","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"key":"28_CR1","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. arXiv preprint arXiv:1903.11027 (2019)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Chabot, F., Chaouch, M., Rabarisoa, J., Teuliere, C., Chateau, T.: Deep Manta: a coarse-to-fine many-task network for joint 2D and 3D vehicle analysis from monocular image. In: CVPR, pp. 2040\u20132049 (2017)","DOI":"10.1109\/CVPR.2017.198"},{"issue":"4","key":"28_CR3","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. TPAMI 40(4), 834\u2013848 (2017)","journal-title":"TPAMI"},{"key":"28_CR4","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: CVPR, pp. 2147\u20132156 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"28_CR5","unstructured":"Chen, X., Kundu, K., Zhu, Y., Berneshawi, A.G., Ma, H., Fidler, S., Urtasun, R.: 3D object proposals for accurate object class detection. In: NIPS, pp. 424\u2013432 (2015)"},{"issue":"5","key":"28_CR6","doi-asserted-by":"publisher","first-page":"1259","DOI":"10.1109\/TPAMI.2017.2706685","volume":"40","author":"X Chen","year":"2017","unstructured":"Chen, X., Kundu, K., Zhu, Y., Ma, H., Fidler, S., Urtasun, R.: 3D object proposals using stereo imagery for accurate object class detection. TPAMI 40(5), 1259\u20131272 (2017)","journal-title":"TPAMI"},{"key":"28_CR7","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":"28_CR8","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":"28_CR9","doi-asserted-by":"crossref","unstructured":"Engelcke, M., Rao, D., Wang, D.Z., Tong, C.H., Posner, I.: Vote3Deep: fast object detection in 3D point clouds using efficient convolutional neural networks. In: ICRA, pp. 1355\u20131361 (2017)","DOI":"10.1109\/ICRA.2017.7989161"},{"key":"28_CR10","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":"28_CR11","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: ICCV, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"28_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"28_CR13","unstructured":"Huang, C., Zhai, S., Talbott, W., Bautista, M.A., Sun, S.Y., Guestrin, C., Susskind, J.: Addressing the loss-metric mismatch with adaptive loss alignment. In: ICML (2019)"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Janssens, R., Zeng, G., Zheng, G.: Fully automatic segmentation of lumbar vertebrae from CT images using cascaded 3D fully convolutional networks. In: ISBI, pp. 893\u2013897 (2018)","DOI":"10.1109\/ISBI.2018.8363715"},{"key":"28_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"816","DOI":"10.1007\/978-3-030-01264-9_48","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Jiang","year":"2018","unstructured":"Jiang, B., Luo, R., Mao, J., Xiao, T., Jiang, Y.: Acquisition of localization confidence for accurate object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 816\u2013832. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_48"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: ICDAR, pp. 1156\u20131160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: ICDAR, pp. 1484\u20131493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"28_CR18","unstructured":"Kosiorek, A., Bewley, A., Posner, I.: Hierarchical attentive recurrent tracking. In: NIPS, pp. 3053\u20133061 (2017)"},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Ku, J., Mozifian, M., Lee, J., Harakeh, A., Waslander, S.L.: Joint 3D proposal generation and object detection from view aggregation. In: IROS, pp. 1\u20138 (2018)","DOI":"10.1109\/IROS.2018.8594049"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Ku, J., Pon, A.D., Waslander, S.L.: Monocular 3D object detection leveraging accurate proposals and shape reconstruction. In: CVPR, pp. 11867\u201311876 (2019)","DOI":"10.1109\/CVPR.2019.01214"},{"key":"28_CR21","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":"28_CR22","doi-asserted-by":"crossref","unstructured":"Li, B.: 3D fully convolutional network for vehicle detection in point cloud. In: IROS, pp. 1513\u20131518 (2017)","DOI":"10.1109\/IROS.2017.8205955"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Li, P., Chen, X., Shen, S.: Stereo R-CNN based 3D object detection for autonomous driving. In: CVPR, pp. 7644\u20137652 (2019)","DOI":"10.1109\/CVPR.2019.00783"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Li, P., Qin, T., et al.: Stereo vision-based semantic 3D object and ego-motion tracking for autonomous driving. In: ECCV, pp. 646\u2013661 (2018)","DOI":"10.1007\/978-3-030-01216-8_40"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: CVPR, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: ICCV, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"28_CR27","unstructured":"Liu, L., Pan, Z., Lei, B.: Learning a rotation invariant detector with rotatable bounding box. arXiv preprint arXiv:1711.09405 (2017)"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Liu, L., Lu, J., Xu, C., Tian, Q., Zhou, J.: Deep fitting degree scoring network for monocular 3D object detection. In: CVPR, pp. 1057\u20131066 (2019)","DOI":"10.1109\/CVPR.2019.00115"},{"key":"28_CR29","doi-asserted-by":"crossref","unstructured":"Liu, X., Liang, D., Yan, S., Chen, D., Qiao, Y., Yan, J.: FOTS: fast oriented text spotting with a unified network. In: CVPR, pp. 5676\u20135685 (2018)","DOI":"10.1109\/CVPR.2018.00595"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Maturana, D., Scherer, S.: VoxNet: a 3D convolutional neural network for real-time object recognition. In: IROS, pp. 922\u2013928 (2015)","DOI":"10.1109\/IROS.2015.7353481"},{"key":"28_CR31","doi-asserted-by":"crossref","unstructured":"Nam, H., Han, B.: Learning multi-domain convolutional neural networks for visual tracking. In: CVPR, pp. 4293\u20134302 (2016)","DOI":"10.1109\/CVPR.2016.465"},{"key":"28_CR32","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 9277\u20139286 (2019)","DOI":"10.1109\/ICCV.2019.00937"},{"key":"28_CR33","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":"28_CR34","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: CVPR, pp. 652\u2013660 (2017)"},{"key":"28_CR35","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: NIPS, pp. 5099\u20135108 (2017)"},{"key":"28_CR36","doi-asserted-by":"crossref","unstructured":"Qin, Z., Wang, J., Lu, Y.: Triangulation learning network: from monocular to stereo 3D object detection. In: CVPR, pp. 11867\u201311876 (2019)","DOI":"10.1109\/CVPR.2019.00780"},{"key":"28_CR37","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp. 91\u201399 (2015)"},{"key":"28_CR38","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: CVPR, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"28_CR39","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"},{"key":"28_CR40","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: Sun RGB-D: a RGB-D scene understanding benchmark suite. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 567\u2013576 (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"28_CR41","doi-asserted-by":"crossref","unstructured":"Tychsen-Smith, L., Petersson, L.: Improving object localization with fitness NMS and bounded IoU loss. In: CVPR, pp. 6877\u20136885 (2018)","DOI":"10.1109\/CVPR.2018.00719"},{"key":"28_CR42","doi-asserted-by":"crossref","unstructured":"Wang, X., Xiao, T., Jiang, Y., Shao, S., Sun, J., Shen, C.: Repulsion loss: detecting pedestrians in a crowd. In: CVPR, pp. 7774\u20137783 (2018)","DOI":"10.1109\/CVPR.2018.00811"},{"key":"28_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Z., Jia, K.: Frustum convNet: sliding frustums to aggregate local point-wise features for a modal 3D object detection. arXiv preprint arXiv:1903.01864 (2019)","DOI":"10.1109\/IROS40897.2019.8968513"},{"key":"28_CR44","doi-asserted-by":"crossref","unstructured":"Xia, G.S., et al.: DOTA: a large-scale dataset for object detection in aerial images. In: CVPR, pp. 3974\u20133983 (2018)","DOI":"10.1109\/CVPR.2018.00418"},{"key":"28_CR45","doi-asserted-by":"crossref","unstructured":"Xu, B., Chen, Z.: Multi-level fusion based 3D object detection from monocular images. In: CVPR, pp. 2345\u20132353 (2018)","DOI":"10.1109\/CVPR.2018.00249"},{"key":"28_CR46","doi-asserted-by":"crossref","unstructured":"Xu, D., Anguelov, D., Jain, A.: PointFusion: deep sensor fusion for 3D bounding box estimation. In: CVPR, pp. 244\u2013253 (2018)","DOI":"10.1109\/CVPR.2018.00033"},{"issue":"10","key":"28_CR47","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":"28_CR48","unstructured":"Yang, X., Liu, Q., Yan, J., Li, A.: R3Det: refined single-stage detector with feature refinement for rotating object. arXiv preprint arXiv:1908.05612 (2019)"},{"key":"28_CR49","doi-asserted-by":"crossref","unstructured":"Yang, X., et al.: SCRDet: towards more robust detection for small, cluttered and rotated objects. In: ICCV, pp. 8232\u20138241 (2019)","DOI":"10.1109\/ICCV.2019.00832"},{"key":"28_CR50","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: UnitBox: an advanced object detection network. In: ACM MM, pp. 516\u2013520 (2016)","DOI":"10.1145\/2964284.2967274"},{"key":"28_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, D., et al.: IoU loss for 2D\/3D object detection. In: 3DV, pp. 85\u201394 (2019)","DOI":"10.1109\/3DV.2019.00019"},{"key":"28_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, J., Lu, X., Tan, X., Shao, Z., Ding, S., Ma, L.: FVNet: 3D front-view proposal generation for real-time object detection from point clouds. arXiv preprint arXiv:1903.10750 (2019)","DOI":"10.1109\/CISP-BMEI48845.2019.8965844"},{"key":"28_CR53","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: CVPR, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"28_CR54","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"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58565-5_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:09:44Z","timestamp":1731283784000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58565-5_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585648","9783030585655"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58565-5_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 November 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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","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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}