{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T14:13:52Z","timestamp":1760710432717,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030660956"},{"type":"electronic","value":"9783030660963"}],"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\/978-3-030-66096-3_45","type":"book-chapter","created":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T07:03:14Z","timestamp":1609570994000},"page":"682-699","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["How to Track Your Dragon: A Multi-attentional Framework for Real-Time RGB-D 6-DOF Object Pose Tracking"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2863-4155","authenticated-orcid":false,"given":"Isidoros","family":"Marougkas","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3183-2726","authenticated-orcid":false,"given":"Petros","family":"Koutras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikos","family":"Kardaris","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6734-3575","authenticated-orcid":false,"given":"Georgios","family":"Retsinas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5055-199X","authenticated-orcid":false,"given":"Georgia","family":"Chalvatzaki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0534-2707","authenticated-orcid":false,"given":"Petros","family":"Maragos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Belagiannis, V., Rupprecht, C., Carneiro, G., Navab, N.: Robust optimization for deep regression. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2830\u20132838 (2015)","DOI":"10.1109\/ICCV.2015.324"},{"issue":"6","key":"45_CR2","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1007\/s11263-017-1052-4","volume":"126","author":"R Br\u00e9gier","year":"2018","unstructured":"Br\u00e9gier, R., Devernay, F., Leyrit, L., Crowley, J.L.: Defining the pose of any 3D rigid object and an associated distance. Int. J. Comput. Vision (IJCV) 126(6), 571\u2013596 (2018)","journal-title":"Int. J. Comput. Vision (IJCV)"},{"key":"45_CR3","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: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"45_CR4","doi-asserted-by":"crossref","unstructured":"Deng, X., Mousavian, A., Xiang, Y., Xia, F., Bretl, T., Fox, D.: Poserbpf: a rao-blackwellized particle filter for 6d object pose tracking. arXiv preprint arXiv:1905.09304 (2019)","DOI":"10.15607\/RSS.2019.XV.049"},{"key":"45_CR5","unstructured":"Doucet, A., De Freitas, N., Murphy, K., Russell, S.: Rao-blackwellised particle filtering for dynamic Bayesian networks. arXiv preprint arXiv:1301.3853 (2013)"},{"key":"45_CR6","unstructured":"Fletcher, T.: Terse notes on riemannian geometry (2010)"},{"issue":"11","key":"45_CR7","doi-asserted-by":"publisher","first-page":"2410","DOI":"10.1109\/TVCG.2017.2734599","volume":"23","author":"M Garon","year":"2017","unstructured":"Garon, M., Lalonde, J.F.: Deep 6-DOF tracking. IEEE Trans. Visual Comput. Graphics 23(11), 2410\u20132418 (2017)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"45_CR8","doi-asserted-by":"crossref","unstructured":"Garon, M., Laurendeau, D., Lalonde, J.F.: A framework for evaluating 6-DOF object trackers. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 582\u2013597 (2018)","DOI":"10.1007\/978-3-030-01252-6_36"},{"key":"45_CR9","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)"},{"issue":"3","key":"45_CR10","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/s11263-012-0601-0","volume":"103","author":"R Hartley","year":"2013","unstructured":"Hartley, R., Trumpf, J., Dai, Y., Li, H.: Rotation averaging. Int. J. of Comp. Vision (IJCV) 103(3), 267\u2013305 (2013)","journal-title":"Int. J. of Comp. Vision (IJCV)"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"45_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"45_CR14","doi-asserted-by":"crossref","unstructured":"Hinterstoisser, S., Lepetit, V., Wohlhart, P., Konolige, K.: On pre-trained image features and synthetic images for deep learning. In: Proceedings of European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-11009-3_42"},{"issue":"2","key":"45_CR15","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s10851-009-0161-2","volume":"35","author":"DQ Huynh","year":"2009","unstructured":"Huynh, D.Q.: Metrics for 3D rotations: comparison and analysis. J. Math. Imaging Vision 35(2), 155\u2013164 (2009)","journal-title":"J. Math. Imaging Vision"},{"key":"45_CR16","unstructured":"Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., Keutzer, K.: Squeezenet: alexnet-level accuracy with 50x fewer parameters and $$<$$0.5mb model size. arXiv:1602.07360 (2016)"},{"key":"45_CR17","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., Brox, T.: Flownet 2.0: evolution of optical flow estimation with deep networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2462\u20132470 (2017)","DOI":"10.1109\/CVPR.2017.179"},{"key":"45_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1007\/978-3-030-20893-6_30","volume-title":"Computer Vision \u2013 ACCV 2018","author":"OH Jafari","year":"2019","unstructured":"Jafari, O.H., Mustikovela, S.K., Pertsch, K., Brachmann, E., Rother, C.: iPose: instance-aware 6D pose estimation of partly occluded objects. In: Jawahar, C.V., Li, H., Mori, G., Schindler, K. (eds.) ACCV 2018. LNCS, vol. 11363, pp. 477\u2013492. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-20893-6_30"},{"key":"45_CR19","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 IEEE International Conference on Computer Vision (ICCV), pp. 1521\u20131529 (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"45_CR20","doi-asserted-by":"crossref","unstructured":"Kendall, A., Gal, Y., Cipolla, R.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7482\u20137491 (2018)","DOI":"10.1109\/CVPR.2018.00781"},{"key":"45_CR21","unstructured":"Leopardi, P.C.: Distributing points on the sphere: partitions, separation, quadrature and energy. Ph.D. thesis, University of New South Wales, Sydney, Australia (2007)"},{"key":"45_CR22","doi-asserted-by":"publisher","unstructured":"Lepetit, V., Moreno-Noguer, F., Fua, P.: EPnP: an accurate O(n) solution to the PnP problem. Int. J. Comput. Vision (IJCV) 81, 155 (2009). https:\/\/doi.org\/10.1007\/s11263-008-0152-6","DOI":"10.1007\/s11263-008-0152-6"},{"key":"45_CR23","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 European Conference on Computer Vision (ECCV), pp. 683\u2013698 (2018)","DOI":"10.1007\/978-3-030-01231-1_42"},{"key":"45_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"45_CR25","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"45_CR26","unstructured":"Loshchilov, I., Hutter, F.: Fixing weight decay regularization in adam. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"45_CR27","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 Workshops, pp. 2174\u20132182 (2017)","DOI":"10.1109\/ICCVW.2017.254"},{"key":"45_CR28","doi-asserted-by":"crossref","unstructured":"Nguyen, C.V., Izadi, S., Lovell, D.: Modeling kinect sensor noise for improved 3D reconstruction and tracking. In: 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission, pp. 524\u2013530. IEEE (2012)","DOI":"10.1109\/3DIMPVT.2012.84"},{"key":"45_CR29","doi-asserted-by":"crossref","unstructured":"Park, K., Patten, T., Vincze, M.: Pix2pose: pixel-wise coordinate regression of objects for 6D pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7668\u20137677 (2019)","DOI":"10.1109\/ICCV.2019.00776"},{"key":"45_CR30","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":"45_CR31","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":"45_CR32","doi-asserted-by":"crossref","unstructured":"Segal, A., Haehnel, D., Thrun, S.: Generalized-ICP. In: Robotics: Science and Systems, Seattle, WA, vol. 2, p. 435 (2009)","DOI":"10.15607\/RSS.2009.V.021"},{"key":"45_CR33","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., Marton, Z.C., Durner, M., Brucker, M., Triebel, R.: Implicit 3D orientation learning for 6D object detection from RGB images. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 699\u2013715 (2018)","DOI":"10.1007\/978-3-030-01231-1_43"},{"issue":"3","key":"45_CR34","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1080\/00401706.1962.10490022","volume":"4","author":"B Welford","year":"1962","unstructured":"Welford, B.: Note on a method for calculating corrected sums of squares and products. Technometrics 4(3), 419\u2013420 (1962)","journal-title":"Technometrics"},{"key":"45_CR35","doi-asserted-by":"crossref","unstructured":"Wohlhart, P., Lepetit, V.: Learning descriptors for object recognition and 3D pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3109\u20133118 (2015)","DOI":"10.1109\/CVPR.2015.7298930"},{"key":"45_CR36","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":"45_CR37","doi-asserted-by":"crossref","unstructured":"Xiao, J., Owens, A., Torralba, A.: SUN3D: a database of big spaces reconstructed using SFM and object labels. In: Proceedings of IEEE International Conference on Computer Vision (ICCV), pp. 1625\u20131632 (2013)","DOI":"10.1109\/ICCV.2013.458"},{"key":"45_CR38","doi-asserted-by":"crossref","unstructured":"Zakharov, S., Shugurov, I., Ilic, S.: DPOD: dense 6D pose object detector in RGB images. arXiv preprint arXiv:1902.11020 (2019)","DOI":"10.1109\/ICCV.2019.00203"},{"key":"45_CR39","doi-asserted-by":"crossref","unstructured":"Zhou, H., Ummenhofer, B., Brox, T.: DeepTAM: deep tracking and mapping. In: Proceedings of European Conference on Computer Vision (ECCV), pp. 822\u2013838 (2018)","DOI":"10.1007\/978-3-030-01270-0_50"},{"key":"45_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5745\u20135753 (2019)","DOI":"10.1109\/CVPR.2019.00589"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66096-3_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T00:16:15Z","timestamp":1735776975000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66096-3_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030660956","9783030660963"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66096-3_45","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":"3 January 2021","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. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","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)"}}]}}