{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:17:23Z","timestamp":1771949843765,"version":"3.50.1"},"publisher-location":"Cham","reference-count":45,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030660956","type":"print"},{"value":"9783030660963","type":"electronic"}],"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_18","type":"book-chapter","created":{"date-parts":[[2021,1,2]],"date-time":"2021-01-02T07:03:14Z","timestamp":1609570994000},"page":"249-263","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Exploiting 3D Hand Pose Estimation in Deep Learning-Based Sign Language Recognition from RGB Videos"],"prefix":"10.1007","author":[{"given":"Maria","family":"Parelli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katerina","family":"Papadimitriou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerasimos","family":"Potamianos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georgios","family":"Pavlakos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Petros","family":"Maragos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,3]]},"reference":[{"key":"18_CR1","unstructured":"ELAN (Version 5.8) [Computer software], Nijmegen: Max Planck Institute for Psycholinguistics, The Language Archive (2019). https:\/\/archive.mpi.nl\/tla\/elan"},{"key":"18_CR2","unstructured":"Adaloglou, N., et al.: A comprehensive study on sign language recognition methods. IEEE Trans. Multimedia (2019)"},{"key":"18_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. CoRR abs\/1409.0473 (2014)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Camgoz, N.C., Hadfield, S., Koller, O., Ney, H., Bowden, R.: Neural sign language translation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7784\u20137793 (2018)","DOI":"10.1109\/CVPR.2018.00812"},{"key":"18_CR5","unstructured":"Camg\u00f6z, N.C., Koller, O., Hadfield, S., Bowden, R.: Sign language transformers: Joint end-to-end sign language recognition and translation. CoRR abs\/2003.13830 (2020)"},{"key":"18_CR6","doi-asserted-by":"crossref","unstructured":"Cho, K., Merrienboer, B.V., G\u00fcl\u00e7ehre, C., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"18_CR7","unstructured":"Community, B.O.: Blender-a 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam (2018). http:\/\/www.blender.org"},{"key":"18_CR8","unstructured":"Crasborn, O., Sloetjes, H.: Enhanced ELAN functionality for sign language corpora. In: Proceedings of the Workshop on the Representation and Processing of Sign Languages: Construction and Exploitation of Sign Language Corpora, pp. 39\u201343 (2008)"},{"key":"18_CR9","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"18_CR10","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi, J., Hazan, E., Singer, Y.: Adaptive subgradient methods for online learning and stochastic optimization. J. Mach. Learn. Res. 12, 2121\u20132159 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Escalera, S., et al.: Chalearn multi-modal gesture recognition 2013: grand challenge and workshop summary. In: Proceedings of the ACM on International Conference on Multimodal Interaction, pp. 365\u2013368 (2013)","DOI":"10.1145\/2522848.2532597"},{"key":"18_CR12","volume-title":"Consumer Depth Cameras for Computer Vision - Research Topics and Applications","year":"2012","unstructured":"Fossati, A., Gall, J., Grabner, H., Ren, X., Konolige, K. (eds.): Consumer Depth Cameras for Computer Vision - Research Topics and Applications. Springer, New York (2012)"},{"key":"18_CR13","unstructured":"Fuse, M.: Mixamo: Quality 3D Character Animation In Minutes (2015). https:\/\/www.mixamo.com"},{"key":"18_CR14","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010)"},{"key":"18_CR15","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 the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"key":"18_CR16","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 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR17","unstructured":"He, Y., Hu, W., Yang, S.F., Qu, X., Wan, P., Guo, Z.: 3D hand pose estimation in the wild via graph refinement under adversarial learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)"},{"key":"18_CR18","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Hosain, A.A., Santhalingam, P.S., Pathak, P., Kosecka, J., Rangwala, H.: Sign language recognition analysis using multimodal data. In: Proceedings of the IEEE International Conference on Data Science and Advanced Analytics, pp. 203\u2013210 (2019)","DOI":"10.1109\/DSAA.2019.00035"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Hu, Y., Zhao, H.F., Wang, Z.G.: Sign language fingerspelling recognition using depth information and deep belief networks. Int. J. Pattern Recogn. Artif. Intell. 32(06) (2018)","DOI":"10.1142\/S0218001418500180"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Kartika, D.R., Sigit, R., Setiawardhana, S.: Sign language interpreter hand using optical-flow. In: Proceedings of the International Seminar on Application for Technology of Information and Communication, pp. 197\u2013201 (2016)","DOI":"10.1109\/ISEMANTIC.2016.7873837"},{"key":"18_CR22","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR abs\/1412.6980 (2014)"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Ko, S., Son, J., Jung, H.: Sign language recognition with recurrent neural network using human keypoint detection. In: Proceedings of the Conference on Research in Adaptive and Convergent Systems, pp. 326\u2013328 (2018)","DOI":"10.1145\/3264746.3264805"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Konstantinidis, D., Dimitropoulos, K., Daras, P.: A deep learning approach for analyzing video and skeletal features in sign language recognition. In: Proceedings of the IEEE International Conference on Imaging Systems and Techniques, pp. 1\u20136 (2018)","DOI":"10.1109\/IST.2018.8577085"},{"key":"18_CR25","unstructured":"Kurakin, A., Zhang, Z., Liu, Z.: A real time system for dynamic hand gesture recognition with a depth sensor. In: Proceedings of the European Signal Processing Conference, pp. 1975\u20131979 (2012)"},{"issue":"3","key":"18_CR26","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1109\/JSEN.2017.2779466","volume":"18","author":"BG Lee","year":"2018","unstructured":"Lee, B.G., Lee, S.M.: Smart wearable hand device for sign language interpretation system with sensors fusion. IEEE Sens. J. 18(3), 1224\u20131232 (2018)","journal-title":"IEEE Sens. J."},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2659\u20132668 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"issue":"16","key":"18_CR28","doi-asserted-by":"publisher","first-page":"7056","DOI":"10.1109\/JSEN.2019.2909837","volume":"19","author":"A Mittal","year":"2019","unstructured":"Mittal, A., Kumar, P., Roy, P.P., Balasubramanian, R., Chaudhuri, B.B.: A modified LSTM model for continuous sign language recognition using leap motion. IEEE Sens. J. 19(16), 7056\u20137063 (2019)","journal-title":"IEEE Sens. J."},{"key":"18_CR29","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 49\u201359 (2018)","DOI":"10.1109\/CVPR.2018.00013"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Nugraha, F., Djamal, E.C.: Video recognition of American sign language using two-stream convolution neural networks. In: Proceedings of the International Conference on Electrical Engineering and Informatics, pp. 400\u2013405 (2019)","DOI":"10.1109\/ICEEI47359.2019.8988872"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Panteleris, P., Oikonomidis, I., Argyros, A.A.: Using a single RGB frame for real time 3D hand pose estimation in the wild. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 436\u2013445 (2018)","DOI":"10.1109\/WACV.2018.00054"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Papadimitriou, K., Potamianos, G.: End-to-end convolutional sequence learning for ASL fingerspelling recognition. In: Proceedings of the Annual Conference of the International Speech Communication Association, pp. 2315\u20132319 (2019)","DOI":"10.21437\/Interspeech.2019-2422"},{"key":"18_CR33","unstructured":"Paszke, A., et al.: Automatic differentiation in PyTorch. In: Proceedings of the NIPS-W (2017)"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Pitsikalis, V., Theodorakis, S., Vogler, C., Maragos, P.: Advances in phonetics-based sub-unit modeling for transcription alignment and sign language recognition. In: Proceedings of the IEEE Computer Vision and Pattern Recognition Workshops, pp. 1\u20136 (2011)","DOI":"10.1109\/CVPRW.2011.5981681"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Ren, Z., Yuan, J., Zhang, Z.: Robust hand gesture recognition based on finger-earth mover\u2019s distance with a commodity depth camera. In: Proceedings of the ACM Multimedia Conference and Co-Located Workshops, pp. 1093\u20131096 (2011)","DOI":"10.1145\/2072298.2071946"},{"key":"18_CR36","first-page":"1627","volume":"14","author":"A Roussos","year":"2013","unstructured":"Roussos, A., Theodorakis, S., Pitsikalis, V., Maragos, P.: Dynamic affine-invariant shape-appearance handshape features and classification in sign language videos. J. Mach. Learn. Res. 14, 1627\u20131663 (2013)","journal-title":"J. Mach. Learn. Res."},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Shi, B., Rio, A.M.D., Keane, J., Brentari, D., Shakhnarovich, G., Livescu, K.: Fingerspelling recognition in the wild with iterative visual attention. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5399\u20135408 (2019)","DOI":"10.1109\/ICCV.2019.00550"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Shi, B., et al.: American sign language fingerspelling recognition in the wild. Proceedings of the IEEE Spoken Language Technology Workshop, pp. 145\u2013152 (2018)","DOI":"10.1109\/SLT.2018.8639639"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4645\u20134653 (2017)","DOI":"10.1109\/CVPR.2017.494"},{"issue":"5","key":"18_CR40","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/MSP.2013.2266959","volume":"30","author":"I Tashev","year":"2013","unstructured":"Tashev, I.: Kinect development kit: a toolkit for gesture- and speech-based human-machine interaction [best of the web]. IEEE Signal Process. Mag. 30(5), 129\u2013131 (2013)","journal-title":"IEEE Signal Process. Mag."},{"key":"18_CR41","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. (NeurIPS) 30, 5998\u20136008 (2017)","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"18_CR42","unstructured":"Wu, Y., et al.: Google\u2019s neural machine translation system: Bridging the gap between human and machine translation. CoRR abs\/1609.08144 (2016)"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Zhou, J., Cao, Y., Wang, X., Li, P., Xu, W.: Deep recurrent models with fast-forward connections for neural machine translation. CoRR abs\/1606.04199 (2016)","DOI":"10.1162\/tacl_a_00105"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4913\u20134921 (2017)","DOI":"10.1109\/ICCV.2017.525"},{"key":"18_CR45","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: FreiHAND: a dataset for markerless capture of hand pose and shape from single RGB images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 813\u2013822 (2019)","DOI":"10.1109\/ICCV.2019.00090"}],"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_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T00:09:45Z","timestamp":1735776585000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66096-3_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030660956","9783030660963"],"references-count":45,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66096-3_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"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)"}}]}}