{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T22:39:12Z","timestamp":1768689552262,"version":"3.49.0"},"publisher-location":"Cham","reference-count":55,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200731","type":"print"},{"value":"9783031200748","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\/978-3-031-20074-8_41","type":"book-chapter","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:23:11Z","timestamp":1668198191000},"page":"715-731","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Semi-supervised Monocular 3D Object Detection by\u00a0Multi-view Consistency"],"prefix":"10.1007","author":[{"given":"Qing","family":"Lian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanbo","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weilong","family":"Yao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingcong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,12]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Bian, J.W., et al.: Unsupervised scale-consistent depth learning from video. In: IJCV (2021)","DOI":"10.1007\/s11263-021-01484-6"},{"key":"41_CR2","doi-asserted-by":"crossref","unstructured":"Brazil, G., Liu, X.: M3D-RPN: monocular 3D region proposal network for object detection. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00938"},{"key":"41_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1007\/978-3-030-58592-1_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Brazil","year":"2020","unstructured":"Brazil, G., Pons-Moll, G., Liu, X., Schiele, B.: Kinematic 3D object detection in\u00a0monocular video. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12368, pp. 135\u2013152. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58592-1_9"},{"key":"41_CR4","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H., Huang, Y., Tian, W., Gao, Z., Xiong, L.: Monorun: monocular 3D object detection by reconstruction and uncertainty propagation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01024"},{"key":"41_CR6","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 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"41_CR7","unstructured":"Chen, X., et al.: 3D object proposals for accurate object class detection. In: NeurIPS (2015)"},{"key":"41_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tai, L., Sun, K., Li, M.: Monopair: monocular 3D object detection using pairwise spatial relationships. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01211"},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Dai, Q., Patil, V., Hecker, S., Dai, D., Van Gool, L., Schindler, K.: Self-supervised object motion and depth estimation from video. In: CVPRW (2020)","DOI":"10.1109\/CVPRW50498.2020.00510"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"41_CR11","doi-asserted-by":"crossref","unstructured":"van Dijk, T., de Croon, G.: How do neural networks see depth in single images? In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00227"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Ding, M., et al.: Learning depth-guided convolutions for monocular 3D object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01169"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Godard, C., Mac Aodha, O., Firman, M., Brostow, G.J.: Digging into self-supervised monocular depth prediction. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00393"},{"key":"41_CR15","unstructured":"Jeong, J., Lee, S., Kim, J., Kwak, N.: Consistency-based semi-supervised learning for object detection. In: NeurIPS (2019)"},{"key":"41_CR16","unstructured":"Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: NeurIPS. Curran Associates, Inc. (2017)"},{"key":"41_CR17","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 (2019)","DOI":"10.1109\/CVPR.2019.01298"},{"key":"41_CR18","unstructured":"Li, H., Gordon, A., Zhao, H., Casser, V., Angelova, A.: Unsupervised monocular depth learning in dynamic scenes. arXiv preprint arXiv:2010.16404 (2020)"},{"key":"41_CR19","doi-asserted-by":"crossref","unstructured":"Li, P., Chen, X., Shen, S.: Stereo R-CNN based 3D object detection for autonomous driving. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00783"},{"key":"41_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"644","DOI":"10.1007\/978-3-030-58580-8_38","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Li","year":"2020","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: RTM3D: real-time monocular 3d\u00a0detection from object keypoints for\u00a0autonomous driving. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 644\u2013660. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_38"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Li, P., Zhao, H., Liu, P., Cao, F.: RTM3D: real-time monocular 3D detection from object keypoints for autonomous driving. arXiv preprint arXiv:2001.03343 (2020)","DOI":"10.1007\/978-3-030-58580-8_38"},{"key":"41_CR22","unstructured":"Lian, Q., Ye, B., Xu, R., Yao, W., Zhang, T.: Geometry-aware data augmentation for monocular 3D object detection. arXiv preprint arXiv:2104.05858 (2021)"},{"key":"41_CR23","unstructured":"Liu, Y.C., et al.: Unbiased teacher for semi-supervised object detection. In: ICLR (2021)"},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhou, D., Lu, F., Fang, J., Zhang, L.: Autoshape: real-time shape-aware monocular 3D object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01535"},{"key":"41_CR25","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Geometry uncertainty projection network for monocular 3D object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00310"},{"key":"41_CR26","doi-asserted-by":"crossref","unstructured":"Luo, S., Dai, H., Shao, L., Ding, Y.: M3DSSD: monocular 3D single stage object detector. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00608"},{"key":"41_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1007\/978-3-030-58601-0_19","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Ma","year":"2020","unstructured":"Ma, X., Liu, S., Xia, Z., Zhang, H., Zeng, X., Ouyang, W.: Rethinking pseudo-LiDAR representation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 311\u2013327. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_19"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Ma, X., Wang, Z., Li, H., Zhang, P., Ouyang, W., Fan, X.: Accurate monocular 3D object detection via color-embedded 3D reconstruction for autonomous driving. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00695"},{"key":"41_CR29","doi-asserted-by":"crossref","unstructured":"Ma, X., et al.: Delving into localization errors for monocular 3D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00469"},{"key":"41_CR30","doi-asserted-by":"crossref","unstructured":"Park, D., Ambrus, R., Guizilini, V., Li, J., Gaidon, A.: Is pseudo-lidar needed for monocular 3D object detection? In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"41_CR31","doi-asserted-by":"crossref","unstructured":"Qian, S., Sun, K., Wu, W., Qian, C., Jia, J.: Aggregation via separation: boosting facial landmark detector with semi-supervised style translation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01025"},{"key":"41_CR32","doi-asserted-by":"crossref","unstructured":"Reading, C., Harakeh, A., Chae, J., Waslander, S.L.: Categorical depth distribution network for monocular 3D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00845"},{"key":"41_CR33","doi-asserted-by":"crossref","unstructured":"Shi, S., et al.: PV-RCNN: point-voxel feature set abstraction for 3D object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01054"},{"key":"41_CR34","doi-asserted-by":"crossref","unstructured":"Shi, S., Wang, X., Li, H.: PointRCNN: 3D object proposal generation and detection from point cloud. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00086"},{"key":"41_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1007\/978-3-030-58526-6_6","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Shi","year":"2020","unstructured":"Shi, X., Chen, Z., Kim, T.-K.: Distance-normalized unified representation for monocular 3D object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 91\u2013107. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58526-6_6"},{"key":"41_CR36","doi-asserted-by":"crossref","unstructured":"Shi, X., et al.: Geometry-based distance decomposition for monocular 3D object detection. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01489"},{"key":"41_CR37","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bul\u00f2, S.R., Porzi, L., Kontschieder, P., Ricci, E.: Are we missing confidence in pseudo-lidar methods for monocular 3D object detection? In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00321"},{"key":"41_CR38","doi-asserted-by":"crossref","unstructured":"Simonelli, A., Bul\u00f2, S.R.R., Porzi, L., L\u00f3pez-Antequera, M., Kontschieder, P.: Disentangling monocular 3D object detection. arXiv preprint arXiv:1905.12365 (2019)","DOI":"10.1109\/ICCV.2019.00208"},{"key":"41_CR39","unstructured":"Sohn, K., Zhang, Z., Li, C.L., Zhang, H., Lee, C.Y., Pfister, T.: A simple semi-supervised learning framework for object detection. arXiv preprint arXiv:2005.04757 (2020)"},{"key":"41_CR40","doi-asserted-by":"crossref","unstructured":"Tang, P., Ramaiah, C., Wang, Y., Xu, R., Xiong, C.: Proposal learning for semi-supervised object detection. In: WACV (2021)","DOI":"10.1109\/WACV48630.2021.00234"},{"key":"41_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., Cong, Y., Litany, O., Gao, Y., Guibas, L.J.: 3DIoUMatch: leveraging IoU prediction for semi-supervised 3D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01438"},{"key":"41_CR42","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: Depth-conditioned dynamic message propagation for monocular 3D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00052"},{"key":"41_CR43","unstructured":"Wang, L., et al.: Progressive coordinate transforms for monocular 3D object detection. In: NeurIPS (2021)"},{"key":"41_CR44","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chao, W.L., Garg, D., Hariharan, B., Campbell, M., Weinberger, K.Q.: Pseudo-lidar from visual depth estimation: bridging the gap in 3D object detection for autonomous driving. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00864"},{"issue":"4","key":"41_CR45","first-page":"600","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. TIP 13(4), 600\u2013612 (2004)","journal-title":"TIP"},{"key":"41_CR46","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"41_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1007\/978-3-319-46493-0_51","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Xie","year":"2016","unstructured":"Xie, J., Girshick, R., Farhadi, A.: Deep3D: fully automatic 2D-to-3D video conversion with deep convolutional neural networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 842\u2013857. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_51"},{"key":"41_CR48","unstructured":"You, Y., et al.: Pseudo-lidar++: accurate depth for 3D object detection in autonomous driving. arXiv preprint arXiv:1906.06310 (2019)"},{"key":"41_CR49","unstructured":"Zhang, F., Pan, T., Wang, B.: Semi-supervised object detection with adaptive class-rebalancing self-training. arXiv preprint arXiv:2107.05031 (2021)"},{"key":"41_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Lu, J., Zhou, J.: Objects are different: flexible monocular 3D object detection. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00330"},{"key":"41_CR51","doi-asserted-by":"crossref","unstructured":"Zhao, N., Chua, T.S., Lee, G.H.: SESS: self-ensembling semi-supervised 3D object detection. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01109"},{"key":"41_CR52","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"41_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1007\/978-3-030-58548-8_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Zhou","year":"2020","unstructured":"Zhou, X., Koltun, V., Kr\u00e4henb\u00fchl, P.: Tracking objects as points. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 474\u2013490. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_28"},{"key":"41_CR54","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. In: arXiv preprint arXiv:1904.07850 (2019)"},{"key":"41_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, Y., He, Y., Zhu, H., Wang, C., Li, H., Jiang, Q.: Monocular 3D object detection: an extrinsic parameter free approach. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00747"}],"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\/978-3-031-20074-8_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T20:33:46Z","timestamp":1668198826000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20074-8_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200731","9783031200748"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20074-8_41","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":"12 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)"}}]}}