{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T23:26:00Z","timestamp":1767137160630,"version":"build-2238731810"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030948924","type":"print"},{"value":"9783030948931","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\/978-3-030-94893-1_24","type":"book-chapter","created":{"date-parts":[[2022,1,22]],"date-time":"2022-01-22T08:02:27Z","timestamp":1642838547000},"page":"507-529","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Regression-Based 3D Hand Pose Estimation for Human-Robot Interaction"],"prefix":"10.1007","author":[{"given":"Chaitanya","family":"Bandi","sequence":"first","affiliation":[]},{"given":"Ulrike","family":"Thomas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,22]]},"reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Bandi, C., Thomas, U.: Regression-based 3D hand pose estimation using heatmaps. In: 15th International Conference on Computer Vision Theory and Applications. SCITEPRESS, Malta (2020)","DOI":"10.5220\/0008973206360643"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Toshev, A., Szegedy, C.: DeepPose: human pose estimation via deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1653\u20131660 (2014)","DOI":"10.1109\/CVPR.2014.214"},{"key":"24_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2629500","volume":"33","author":"J Tompson","year":"2014","unstructured":"Tompson, J., Stein, M., Lecun, Y., Perlin, K.: Real-time continuous pose recovery of human hands using convolutional networks. ACM Trans. Graph. 33, 1\u201310 (2014)","journal-title":"ACM Trans. Graph."},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Wei, S., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4724\u20134732 (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C.-H., Ramanan, D.: 3D Human pose estimation = 2d pose estimation + matching. arXiv preprint arXiv:1612.06524 (2016)","DOI":"10.1109\/CVPR.2017.610"},{"key":"24_CR6","unstructured":"Chen, X., Yuille, A.L.: Articulated pose estimation by a graphical model with image dependent pairwise relations. In: Proceedings of the Conference on Neural Information Processing Systems (NIPS), pp. 1736\u20131744 (2014)"},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Qian, C., Sun, X., Wei, Y., Tang, X., Sun, J.: Realtime and robust hand tracking from depth. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.145"},{"key":"24_CR8","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. arXiv:1705.01389v3 [cs.CV] (2017)","DOI":"10.1109\/ICCV.2017.525"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Mueller, F., et al.: GANerated hands for real-time 3D hand tracking from monocular RGB. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00013"},{"key":"24_CR10","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Ceylan, D., Yang, J., Russell, B.C., Argus, M.J., Brox, T.: FreiHAND: a dataset for markerless capture of hand pose and shape from single RGB images. In: The IEEE International Conference on Computer Vision (ICCV), pp. 813\u2013822 (2019)","DOI":"10.1109\/ICCV.2019.00090"},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Hampali, S., Oberweger, M., Rad, M., Lepetit, V.: HOnnotate: a method for 3D annotation of hand and object poses. In: Proceedings of CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"24_CR12","unstructured":"Github source. https:\/\/github.com\/eriklindernoren\/PyTorch-YOLOv3. Accessed 29 July 2020"},{"key":"24_CR13","doi-asserted-by":"crossref","unstructured":"Tome, D., Russell, C., Agapito L.: Lifting from the deep: convolutional 3D pose estimation from a single image. arXiv preprint arXiv:1701.00295 (2017)","DOI":"10.1109\/CVPR.2017.603"},{"key":"24_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Bogo","year":"2016","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34"},{"key":"24_CR15","unstructured":"Oberweger, M., Wohlhart, P., Lepetit. V.: Hands deep in deep learning for hand pose estimation. arXiv preprint arXiv:1502.06807 (2015)"},{"key":"24_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1007\/978-3-030-01261-8_29","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L Ge","year":"2018","unstructured":"Ge, L., Ren, Z., Yuan, J.: Point-to-point regression pointnet for 3D hand pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 489\u2013505. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_29"},{"key":"24_CR17","unstructured":"Liuhao, G., Yujun, C., Junwu, W., Junsong, Y.: Hand pointnet: 3D hand pose estimation using point sets. In CVPR (2018)"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Li, S., Lee, D.: Point-to-pose voting based hand pose estimation using residual permutation equivariant layer. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01220"},{"key":"24_CR19","unstructured":"Ren, P., Sun, H., Qi, Q., Wang, J., Huang, W.: SRN: stacked regression network for real-time 3D hand pose estimation. In: Proceedings of BMVC, pp. 1\u201314 (2019)"},{"key":"24_CR20","doi-asserted-by":"crossref","unstructured":"Yuan, S., Stenger, B., Kim, T.-K.: RGB-based 3D hand pose estimation via privileged learning with depth images. arXiv preprint arXiv:1811.07376 (2018)","DOI":"10.1109\/ICCVW.2019.00348"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Huang, W., Ren, P., Wang, J., Qi, Q., Sun. H.: AWR: adaptive weighting regression for 3D hand pose. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6761"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Boukhayma, A., Bem, R.-D., Torr, P.-H.S.: 3D hand shape and pose from images in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01110"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, Q., Mo, H., Zhang, W., Zheng, W.: End-to-end hand mesh recovery from a monocular RGB image. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00244"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"Tang, D., Chang, H.J., Tejani, A., Kim, T.-K.: Latent regression forest: structural estimation of 3D articulated hand posture. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Columbus, Ohio, USA (2014)","DOI":"10.1109\/CVPR.2014.490"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Sun, X., Wei, Y., Liang, S., Tang, X., Sun, J.: Cascaded hand pose regression. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298683"},{"key":"24_CR26","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":"24_CR27","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"24_CR28","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 (CVPR), pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR29","unstructured":"Howard, A.-G, et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"24_CR30","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"24_CR31","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 580\u2013587 (2014)","DOI":"10.1109\/CVPR.2014.81"},{"key":"24_CR32","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NIPS), pp. 91\u201399 (2015)"},{"key":"24_CR33","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":"24_CR34","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), pp. 779\u2013 788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Dollar, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"24_CR36","unstructured":"Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"24_CR37","unstructured":"Bochkovskiy, A., Wang, C.-Y., Mark Liao, H.-Y.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"24_CR38","unstructured":"Github source. https:\/\/github.com\/ultralytics\/yolov5. Accessed 29 July 2020"},{"key":"24_CR39","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: ICCV (2015)","DOI":"10.1109\/ICCV.2015.226"},{"key":"24_CR40","doi-asserted-by":"crossref","unstructured":"Zhou, X., Huang, Q., Sun, X., Xue, X., Wei, Y.,: Towards 3D human pose estimation in the wild: a weakly-supervised approach. Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science, Fudan University, The University of Texas at Austin, Microsoft Research arXiv:1704.02447v2 [cs.CV] (2017)","DOI":"10.1109\/ICCV.2017.51"},{"key":"24_CR41","unstructured":"Github source. https:\/\/github.com\/shreyashampali\/HOnnotate. Accessed 29 July 2020"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.-T., Wang, G.: NTU RGB+ D: a large scale dataset for 3D human activity analysis. In: CVPR, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Colledanchise, M., \u00d6gren, P.: Behavior trees in robotics and AI: an introduction. arXiv preprint arXiv:1709.00084 (2018)","DOI":"10.1201\/9780429489105"},{"key":"24_CR44","unstructured":"Tieleman, T., Hinton, G.: Lecture 6.5 - RMSProp, COURSERA: neural networks for machine learning. Technical report (2012)"}],"updated-by":[{"DOI":"10.1007\/978-3-030-94893-1_26","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000}}],"container-title":["Communications in Computer and Information Science","Computer Vision, Imaging and Computer Graphics Theory and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-94893-1_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,30]],"date-time":"2022-12-30T14:08:43Z","timestamp":1672409323000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-94893-1_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030948924","9783030948931"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-94893-1_24","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"22 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"1 January 2022","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"In the originally published version of chapter 24, the acknowledgements section was erroneously omitted. The acknowledgements section and grant number have been added.","order":4,"name":"change_details","label":"Change Details","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"VISIGRAPP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Joint Conference on Computer Vision, Imaging and Computer Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Valletta","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malta","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":"27 February 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 February 2020","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":"visigrapp2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.visigrapp.org\/?y=2020","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":"PRIMORIS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"455","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":"25","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":"5% - 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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}