{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T09:06:07Z","timestamp":1742979967711,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030907389"},{"type":"electronic","value":"9783030907396"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-90739-6_6","type":"book-chapter","created":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T00:03:39Z","timestamp":1637107419000},"page":"85-106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Pose Tracking vs. Pose Estimation of AR Glasses with Convolutional, Recurrent, and Non-local Neural Networks: A\u00a0Comparison"],"prefix":"10.1007","author":[{"given":"Ahmet","family":"Firintepe","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sarfaraz","family":"Habib","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alain","family":"Pagani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Didier","family":"Stricker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,11,17]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Berg, A., Oskarsson, M., O\u2019Connor, M.: Deep ordinal regression with label diversity. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp. 2740\u20132747 (2021)","DOI":"10.1109\/ICPR48806.2021.9412608"},{"issue":"3","key":"6_CR2","doi-asserted-by":"publisher","first-page":"596","DOI":"10.1109\/TPAMI.2018.2885472","volume":"42","author":"G Borghi","year":"2018","unstructured":"Borghi, G., Fabbri, M., Vezzani, R., Calderara, S., Cucchiara, R.: Face-from-depth for head pose estimation on depth images. IEEE Trans. Pattern Anal. Mach. Intell. 42(3), 596\u2013609 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Borghi, G., Gasparini, R., Vezzani, R., Cucchiara, R.: Embedded recurrent network for head pose estimation in car. In: 2017 IEEE Intelligent Vehicles Symposium (IV), pp. 1503\u20131508. IEEE (2017)","DOI":"10.1109\/IVS.2017.7995922"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Borghi, G., Venturelli, M., Vezzani, R., Cucchiara, R.: Poseidon: face-from-depth for driver pose estimation. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), July 2017","DOI":"10.1109\/CVPR.2017.583"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Capellen, C., Schwarz, M., Behnke, S.: ConvPoseCNN: dense convolutional 6D object pose estimation, pp. 162\u2013172 (2020)","DOI":"10.5220\/0008990901620172"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Chen, B., Parra, A., Cao, J., Li, N., Chin, T.J.: End-to-end learnable geometric vision by backpropagating PnP optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8100\u20138109 (2020)","DOI":"10.1109\/CVPR42600.2020.00812"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1800\u20131807 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"issue":"6","key":"6_CR8","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1109\/TRO.2020.3001674","volume":"36","author":"G Costante","year":"2020","unstructured":"Costante, G., Mancini, M.: Uncertainty estimation for data-driven visual odometry. IEEE Trans. Rob. 36(6), 1738\u20131757 (2020)","journal-title":"IEEE Trans. Rob."},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2758\u20132766 (2015)","DOI":"10.1109\/ICCV.2015.316"},{"issue":"3","key":"6_CR10","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/s11263-012-0549-0","volume":"101","author":"G Fanelli","year":"2013","unstructured":"Fanelli, G., Dantone, M., Gall, J., Fossati, A., Gool, L.: Random forests for real time 3D face analysis. Int. J. Comput. Vision 101(3), 437\u2013458 (2013)","journal-title":"Int. J. Comput. Vision"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Firintepe, A., Mohamed, S., Pagani, A., Stricker, D.: The more, the merrier? A study on in-car IR-based head pose estimation. In: 2020 IEEE Intelligent Vehicles Symposium (IV). IEEE (2020)","DOI":"10.1109\/IV47402.2020.9304545"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Firintepe, A., Pagani, A., Stricker, D.: HMDPose: a large-scale trinocular IR augmented reality glasses pose dataset. In: 26th ACM Symposium on Virtual Reality Software and Technology. ACM (2020)","DOI":"10.1145\/3385956.3422121"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Firintepe, A., Pagani, A., Stricker, D.: A comparison of single and multi-view IR image-based AR glasses pose estimation approaches. In: 2021 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), pp. 571\u2013572 (2021)","DOI":"10.1109\/VRW52623.2021.00168"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Firintepe, A., Vey, C., Asteriadis, S., Pagani, A., Stricker, D.: From IR images to point clouds to pose: point cloud-based AR glasses pose estimation. J. Imag. 7(5) (2021). https:\/\/www.mdpi.com\/2313-433X\/7\/5\/80","DOI":"10.3390\/jimaging7050080"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Gao, G., Lauri, M., Wang, Y., Hu, X., Zhang, J., Frintrop, S.: 6D object pose regression via supervised learning on point clouds. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 3643\u20133649 (2020)","DOI":"10.1109\/ICRA40945.2020.9197461"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Gu, J., Yang, X., De Mello, S., Kautz, J.: Dynamic facial analysis: from Bayesian filtering to recurrent neural network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1531\u20131540 (2017)","DOI":"10.1109\/CVPR.2017.167"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778, June 2016","DOI":"10.1109\/CVPR.2016.90"},{"key":"6_CR18","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2938\u20132946 (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization, pp. 2938\u20132946, December 2015","DOI":"10.1109\/ICCV.2015.336"},{"key":"6_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/978-3-030-01231-1_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Li","year":"2018","unstructured":"Li, Y., Wang, G., Ji, X., Xiang, Yu., Fox, D.: DeepIM: deep iterative matching for 6D pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 695\u2013711. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_42"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, G., Ji, X.: CDPN: coordinates-based disentangled pose network for real-time RGB-Based 6-DoF object pose estimation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7677\u20137686 (2019)","DOI":"10.1109\/ICCV.2019.00777"},{"issue":"2","key":"6_CR23","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1109\/TITS.2010.2044241","volume":"11","author":"E Murphy-Chutorian","year":"2010","unstructured":"Murphy-Chutorian, E., Trivedi, M.M.: Head pose estimation and augmented reality tracking: an integrated system and evaluation for monitoring driver awareness. IEEE Trans. Intell. Transp. Syst. 11(2), 300\u2013311 (2010)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Ning, G., et al.: Spatially supervised recurrent convolutional neural networks for visual object tracking, pp. 1\u20134 (2017)","DOI":"10.1109\/ISCAS.2017.8050867"},{"key":"6_CR25","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\/CVF International Conference on Computer Vision, pp. 7668\u20137677 (2019)","DOI":"10.1109\/ICCV.2019.00776"},{"key":"6_CR26","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: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2019","DOI":"10.1109\/CVPR.2019.00469"},{"key":"6_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/978-3-319-46448-0_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"X Peng","year":"2016","unstructured":"Peng, X., Feris, R.S., Wang, X., Metaxas, D.N.: A recurrent encoder-decoder network for sequential face alignment. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 38\u201356. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_3"},{"key":"6_CR28","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: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3848\u20133856, October 2017","DOI":"10.1109\/ICCV.2017.413"},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2016","DOI":"10.1109\/CVPR.2016.91"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Schwarz, A., Haurilet, M., Martinez, M., Stiefelhagen, R.: DriveAHead-a large-scale driver head pose dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 1\u201310, July 2017","DOI":"10.1109\/CVPRW.2017.155"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Selim, M., Firintepe, A., Pagani, A., Stricker, D.: AutoPOSE: large-scale automotive driver head pose and gaze dataset with deep head pose baseline. In: International Conference on Computer Vision Theory and Applications (VISAPP). SCITEPRESS Digital Library (2020)","DOI":"10.5220\/0009330105990606"},{"key":"6_CR32","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2015)"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Song, C., Song, J., Huang, Q.: HybridPose: 6D object pose estimation under hybrid representations. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 428\u2013437 (2020)","DOI":"10.1109\/CVPR42600.2020.00051"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Tekin, B., Sinha, S.N., Fua, P.: Real-time seamless single shot 6D object pose prediction. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 292\u2013301, June 2018","DOI":"10.1109\/CVPR.2018.00038"},{"key":"6_CR35","unstructured":"Tremblay, J., To, T., Sundaralingam, B., Xiang, Y., Fox, D., Birchfield, S.: Deep object pose estimation for semantic robotic grasping of household objects. In: Proceedings of the 2nd Conference on Robot Learning. Proceedings of Machine Learning Research, vol. 87, pp. 306\u2013316. PMLR, 29\u201331 October 2018"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Wang, S., Clark, R., Wen, H., Trigoni, N.: DeepVO: towards end-to-end visual odometry with deep Recurrent Convolutional Neural Networks. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 2043\u20132050 (2017)","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"6_CR38","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. In: Kress-Gazit, H., Srinivasa, S.S., Howard, T., Atanasov, N. (eds.) Robotics: Science and Systems XIV, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA, 26\u201330 June 2018 (2018)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"6_CR39","unstructured":"Xu, Z., Chen, K., Jia, K.: W-PoseNet: dense correspondence regularized pixel pair pose regression. arXiv preprint arXiv:1912.11888 (2019)"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Zakharov, S., Shugurov, I., Ilic, S.: DPOD: 6D pose object detector and refiner. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1941\u20131950 (2019)","DOI":"10.1109\/ICCV.2019.00203"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Ming, Y., Zhang, R.: Object detection and tracking based on recurrent neural networks. In: 2018 14th IEEE International Conference on Signal Processing (ICSP), pp. 338\u2013343. IEEE (2018)","DOI":"10.1109\/ICSP.2018.8652389"},{"key":"6_CR42","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1007\/978-3-030-58568-6_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zou","year":"2020","unstructured":"Zou, Y., Ji, P., Tran, Q.-H., Huang, J.-B., Chandraker, M.: Learning monocular visual odometry via self-supervised long-term modeling. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 710\u2013727. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_42"}],"container-title":["Lecture Notes in Computer Science","Virtual Reality and Mixed Reality"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-90739-6_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,17]],"date-time":"2021-11-17T00:05:43Z","timestamp":1637107543000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-90739-6_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030907389","9783030907396"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-90739-6_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"17 November 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EuroXR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Virtual Reality and Mixed Reality","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eurovr2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.euroxr-association.org\/conference2021\/","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":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31","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":"8","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":"4","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":"26% - 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":"3","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)"}}]}}