{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T10:18:45Z","timestamp":1769163525933,"version":"3.49.0"},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030012151","type":"print"},{"value":"9783030012168","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"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":[[2018]]},"DOI":"10.1007\/978-3-030-01216-8_26","type":"book-chapter","created":{"date-parts":[[2018,10,8]],"date-time":"2018-10-08T15:10:26Z","timestamp":1539011426000},"page":"426-441","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Efficient 6-DoF Tracking of Handheld Objects from an Egocentric Viewpoint"],"prefix":"10.1007","author":[{"given":"Rohit","family":"Pandey","sequence":"first","affiliation":[]},{"given":"Pavel","family":"Pidlypenskyi","sequence":"additional","affiliation":[]},{"given":"Shuoran","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Christine","family":"Kaeser-Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,9]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Bambach, S., Lee, S., Crandall, D.J., Yu, C.: Lending a hand: detecting hands and recognizing activities in complex egocentric interactions. In: IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.226"},{"key":"26_CR2","unstructured":"Beck, C., Broun, A., Mirmehdi, M., Pipe, T., Melhuish, C.: Text line aggregation. In: The 3rd International Conference on Pattern Recognition Applications and Methods (2014)"},{"issue":"3","key":"26_CR3","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1177\/027836499101000305","volume":"10","author":"JC Chou","year":"1991","unstructured":"Chou, J.C., Kamel, M.: Finding the position and orientation of a sensor on a robot manipulator using quaternions. Int. J. Robot. Res. 10(3), 240\u2013254 (1991)","journal-title":"Int. J. Robot. Res."},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Garcia-Hernando, G., Yuan, S., Baek, S., Kim, T.K.: First-person hand action benchmark with RGB-D videos and 3D hand pose annotations. arXiv preprint arXiv:1704.02463 (2017)","DOI":"10.1109\/CVPR.2018.00050"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? The KITTI vision benchmark suite. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2012)","DOI":"10.1109\/CVPR.2012.6248074"},{"key":"26_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"26_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. arXiv preprint arXiv:1703.06870 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"26_CR8","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":"26_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1007\/978-3-319-49409-8_52","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"T Hoda\u0148","year":"2016","unstructured":"Hoda\u0148, T., Matas, J., Obdr\u017e\u00e1lek, \u0160.: On evaluation of 6D object pose estimation. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 606\u2013619. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_52"},{"key":"26_CR10","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.351"},{"key":"26_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: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"26_CR13","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"26_CR14","doi-asserted-by":"crossref","unstructured":"Liu, S., Wang, S., Wu, L., Jiang, S.: Multiple feature fusion based hand-held object recognition with RGB-D data. In: International Conference on Internet Multimedia Computing and Service (2014)","DOI":"10.1145\/2632856.2632947"},{"key":"26_CR15","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":"26_CR16","doi-asserted-by":"crossref","unstructured":"Mahendran, S., Ali, H., Vidal, R.: 3D pose regression using convolutional neural networks. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCVW.2017.254"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Mousavian, A., Anguelov, D., Flynn, J., Ko\u0161eck\u00e1, J.: 3D bounding box estimation using deep learning and geometry. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.597"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"Mueller, F., Mehta, D., Sotnychenko, O., Sridhar, S., Casas, D., Theobalt, C.: Real-time hand tracking under occlusion from an egocentric RGB-D sensor. In: IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.131"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"Poirson, P., Ammirato, P., Fu, C.Y., Liu, W., Kosecka, J., Berg, A.C.: Fast single shot detection and pose estimation. In: IEEE International Conference on 3D Vision (3DV) (2016)","DOI":"10.1109\/3DV.2016.78"},{"key":"26_CR20","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"26_CR21","doi-asserted-by":"crossref","unstructured":"Rivera-Rubio, J., Idrees, S., Alexiou, I., Hadjilucas, L., Bharath, A.A.: Small hand-held object recognition test. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2014)","DOI":"10.1109\/WACV.2014.6836057"},{"key":"26_CR22","unstructured":"Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. arXiv preprint arXiv:1703.01365 (2017)"},{"key":"26_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1007\/978-3-319-10599-4_30","volume-title":"Computer Vision \u2013 ECCV 2014","author":"A Tejani","year":"2014","unstructured":"Tejani, A., Tang, D., Kouskouridas, R., Kim, T.-K.: Latent-class hough forests for 3D object detection and pose estimation. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 462\u2013477. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10599-4_30"},{"key":"26_CR24","unstructured":"VICON: Vicon motion capture software. https:\/\/www.vicon.com\/products\/software\/tracker. Accessed 13 Mar 2018"},{"key":"26_CR25","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Mottaghi, R., Savarese, S.: Beyond PASCAL: a benchmark for 3D object detection in the wild. In: IEEE Winter Conference on Applications of Computer Vision (WACV) (2014)","DOI":"10.1109\/WACV.2014.6836101"},{"key":"26_CR26","doi-asserted-by":"crossref","unstructured":"Yuan, S., Ye, Q., Stenger, B., Jain, S., Kim, T.K.: BigHand2. 2M benchmark: hand pose dataset and state of the art analysis. arXiv preprint arXiv:1704.02612 (2017)","DOI":"10.1109\/CVPR.2017.279"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2018"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01216-8_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,8]],"date-time":"2022-10-08T00:24:58Z","timestamp":1665188698000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-01216-8_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030012151","9783030012168"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01216-8_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"9 October 2018","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":"Munich","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2018.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}