{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:40:32Z","timestamp":1760136032239,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030606329"},{"type":"electronic","value":"9783030606336"}],"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\/978-3-030-60633-6_15","type":"book-chapter","created":{"date-parts":[[2020,10,10]],"date-time":"2020-10-10T18:02:37Z","timestamp":1602352957000},"page":"180-192","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["GCVNet: Geometry Constrained Voting Network to Estimate 3D Pose for Fine-Grained Object Categories"],"prefix":"10.1007","author":[{"given":"Yaohang","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijun","family":"Di","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanfeng","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianyong","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Gong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,11]]},"reference":[{"key":"15_CR1","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/978-3-319-10605-2_35","volume-title":"European Conference on Computer Vision","author":"E Brachmann","year":"2014","unstructured":"Brachmann, E., Krull, A., Michel, F., Gumhold, S., Shotton, J., Rother, C.: Learning 6D object pose estimation using 3D object coordinates. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) European Conference on Computer Vision, pp. 536\u2013551. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_35"},{"key":"15_CR2","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2147\u20132156 (2016)","DOI":"10.1109\/CVPR.2016.236"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, F.F.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2009), 20\u201325 June 2009, Miami, Florida, USA (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"15_CR4","unstructured":"Elhoseiny, M., El-Gaaly, T., Bakry, A., Elgammal, A.: A comparative analysis and study of multiview cnn models for joint object categorization and pose estimation. In: International Conference on Machine Learning, pp. 888\u2013897 (2016)"},{"key":"15_CR5","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: 2015 IEEE International Conference on Computer Vision (ICCV) (2016)","DOI":"10.1109\/ICCV.2015.169"},{"key":"15_CR6","doi-asserted-by":"crossref","unstructured":"Grabner, A., Roth, P.M., Lepetit, V.: GP2C: geometric projection parameter consensus for joint 3d pose and focal length estimation in the wild. In: The IEEE International Conference on Computer Vision (ICCV), October 2019","DOI":"10.1109\/ICCV.2019.00231"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Grimson, W., Lozano-Perez, T.: Recognition and localization of overlapping parts from sparse data in two and three dimensions. In: Proceedings. 1985 IEEE International Conference on Robotics and Automation, vol. 2, pp. 61\u201366. IEEE (1985)","DOI":"10.1109\/ROBOT.1985.1087320"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Jian, S.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"15_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/978-3-642-37331-2_42","volume-title":"Computer Vision \u2013 ACCV 2012","author":"S Hinterstoisser","year":"2013","unstructured":"Hinterstoisser, S., et al.: Model based training, detection and pose estimation of texture-less 3d objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 548\u2013562. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37331-2_42"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"Hu, Y., Hugonot, J., Fua, P., Salzmann, M.: Segmentation-driven 6D object pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3385\u20133394 (2019)","DOI":"10.1109\/CVPR.2019.00350"},{"key":"15_CR11","unstructured":"Jian, S.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision & Pattern Recognition (2016)"},{"key":"15_CR12","doi-asserted-by":"crossref","unstructured":"Kehl, W., Manhardt, F., Tombari, F., Ilic, S., Navab, N.: SSD-6D: making RGB-based 3D detection and 6d pose estimation great again. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1521\u20131529 (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"15_CR14","doi-asserted-by":"crossref","unstructured":"Lai, K., Bo, L., Ren, X., Fox, D.: A scalable tree-based approach for joint object and pose recognition. In: Twenty-Fifth AAAI Conference on Artificial Intelligence (2011)","DOI":"10.1609\/aaai.v25i1.7986"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, G., Ji, X., Xiang, Y., Fox, D.: DeepIM: deep iterative matching for 6D pose estimation. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 683\u2013698 (2018)","DOI":"10.1007\/978-3-030-01231-1_42"},{"issue":"3","key":"15_CR16","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/0004-3702(87)90070-1","volume":"31","author":"DG Lowe","year":"1987","unstructured":"Lowe, D.G.: Three-dimensional object recognition from single two-dimensional images. Artif. Intell. 31(3), 355\u2013395 (1987)","journal-title":"Artif. Intell."},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Mahendran, S., Ali, H., Vidal, R.: 3D pose regression using convolutional neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2174\u20132182 (2017)","DOI":"10.1109\/ICCVW.2017.254"},{"key":"15_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-030-01267-0_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Oberweger","year":"2018","unstructured":"Oberweger, M., Rad, M., Lepetit, V.: Making deep heatmaps robust to partial occlusions for 3D object pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 125\u2013141. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_8"},{"key":"15_CR19","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Chan, A., Derpanis, K.G., Daniilidis, K.: 6-DoF object pose from semantic keypoints. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2011\u20132018. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989233"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Peng, S., Liu, Y., Huang, Q., Zhou, X., Bao, H.: PVNet: pixel-wise voting network for 6DoF pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4561\u20134570 (2019)","DOI":"10.1109\/CVPR.2019.00469"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Rad, M., Lepetit, V.: Bb8: a scalable, accurate, robust to partial occlusion method for predicting the 3D poses of challenging objects without using depth. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3828\u20133836 (2017)","DOI":"10.1109\/ICCV.2017.413"},{"key":"15_CR22","unstructured":"Schneiderman, H., Kanade, T.: A statistical approach to 3D object detection applied to faces and cars. Carnegie Mellon University, The Robotics Institute (2000)"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Shahrokni, A., Vacchetti, L., Lepetit, V., Fua, P.: Polyhedral object detection and pose estimation for augmented reality applications. In: Proceedings of Computer Animation 2002 (CA 2002), pp. 65\u201369. IEEE (2002)","DOI":"10.1109\/CA.2002.1017508"},{"issue":"4","key":"15_CR24","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1109\/34.588001","volume":"19","author":"I Shimshoni","year":"1997","unstructured":"Shimshoni, I., Ponce, J.: Finite-resolution aspect graphs of polyhedral objects. IEEE Trans. Pattern Anal. Mach. Intell. 19(4), 315\u2013327 (1997)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Sochor, J., Herout, A., Havel, J.: BoxCars: 3D boxes as CNN input for improved fine-grained vehicle recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3006\u20133015 (2016)","DOI":"10.1109\/CVPR.2016.328"},{"key":"15_CR26","doi-asserted-by":"crossref","unstructured":"Su, H., Qi, C.R., Li, Y., Guibas, L.J.: Render for CNN: viewpoint estimation in images using CNNs trained with rendered 3D model views. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2686\u20132694 (2015)","DOI":"10.1109\/ICCV.2015.308"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Tekin, B., Sinha, S.N., Fua, P.: Real-time seamless single shot 6D object pose prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 292\u2013301 (2018)","DOI":"10.1109\/CVPR.2018.00038"},{"key":"15_CR28","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Malik, J.: Viewpoints and keypoints. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1510\u20131519 (2015)","DOI":"10.1109\/CVPR.2015.7298758"},{"key":"15_CR29","doi-asserted-by":"crossref","unstructured":"Varley, J., DeChant, C., Richardson, A., Ruales, J., Allen, P.: Shape completion enabled robotic grasping. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2442\u20132447. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206060"},{"key":"15_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/978-3-030-11009-3_38","volume-title":"Computer Vision \u2013 ECCV 2018 Workshops","author":"Y Wang","year":"2019","unstructured":"Wang, Y., et al.: 3D pose estimation for fine-grained object categories. In: Leal-Taix\u00e9, L., Roth, S. (eds.) ECCV 2018. LNCS, vol. 11129, pp. 619\u2013632. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-11009-3_38"},{"key":"15_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/978-3-319-46466-4_22","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Wu","year":"2016","unstructured":"Wu, J., et al.: Single image 3D interpreter network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 365\u2013382. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_22"},{"key":"15_CR32","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: PoseCNN: a convolutional neural network for 6D object pose estimation in cluttered scenes. arXiv preprint arXiv:1711.00199 (2017)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"15_CR33","doi-asserted-by":"crossref","unstructured":"Yang, L., Luo, P., Change Loy, C., Tang, X.: A large-scale car dataset for fine-grained categorization and verification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3973\u20133981 (2015)","DOI":"10.1109\/CVPR.2015.7299023"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60633-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:05:37Z","timestamp":1760133937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-60633-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030606329","9783030606336"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60633-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"11 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"16 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.prcv.cn\/index_en.html","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":"Microsoft CMT system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"402","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":"158","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":"39% - 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":"4","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)"}}]}}