{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T00:58:11Z","timestamp":1740099491552,"version":"3.37.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030260606"},{"type":"electronic","value":"9783030260613"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-26061-3_20","type":"book-chapter","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T19:03:54Z","timestamp":1565291034000},"page":"191-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Method for Multimodal Recognition of One-Handed Sign Language Gestures Through 3D Convolution and LSTM Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1196-1117","authenticated-orcid":false,"given":"Ildar","family":"Kagirov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7935-0569","authenticated-orcid":false,"given":"Dmitry","family":"Ryumin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7479-2851","authenticated-orcid":false,"given":"Alexandr","family":"Axyonov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,24]]},"reference":[{"key":"20_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/978-3-319-58703-5_7","volume-title":"Universal Access in Human\u2013Computer Interaction. Designing Novel Interactions","author":"D Ryumin","year":"2017","unstructured":"Ryumin, D., Karpov, A.A.: Towards automatic recognition of sign language gestures using kinect 2.0. In: Antona, M., Stephanidis, C. (eds.) UAHCI 2017. LNCS, vol. 10278, pp. 89\u2013101. Springer, Cham (2017). \n                    https:\/\/doi.org\/10.1007\/978-3-319-58703-5_7"},{"key":"20_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1007\/978-3-642-39188-0_56","volume-title":"Universal Access in Human-Computer Interaction. Design Methods, Tools, and Interaction Techniques for eInclusion","author":"A Karpov","year":"2013","unstructured":"Karpov, A., Krnoul, Z., Zelezny, M., Ronzhin, A.: Multimodal synthesizer for Russian and Czech sign languages and audio-visual speech. In: Stephanidis, C., Antona, M. (eds.) UAHCI 2013. LNCS, vol. 8009, pp. 520\u2013529. Springer, Heidelberg (2013). \n                    https:\/\/doi.org\/10.1007\/978-3-642-39188-0_56"},{"key":"20_CR3","doi-asserted-by":"crossref","unstructured":"Ryumin, D., Ivanko, D., Axyonov, A., Kagirov, I., Karpov, A., Zelezny, M.: Human-robot interaction with smart shopping trolley using sign language: data collection. In: Proceedings of IEEE International Conference on Pervasive Computing and Communications, PerCom-2019, Kyoto, Japan (2019, in press)","DOI":"10.1109\/PERCOMW.2019.8730886"},{"key":"20_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1007\/978-3-319-58071-5_44","volume-title":"Human-Computer Interaction. User Interface Design, Development and Multimodality","author":"W Lin","year":"2017","unstructured":"Lin, W., Du, L., Harris-Adamson, C., Barr, A., Rempel, D.: Design of hand gestures for manipulating objects in virtual reality. In: Kurosu, M. (ed.) HCI 2017. LNCS, vol. 10271, pp. 584\u2013592. Springer, Cham (2017). \n                    https:\/\/doi.org\/10.1007\/978-3-319-58071-5_44"},{"key":"20_CR5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.-E., Sheikh, Y.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR-2018, arXiv preprint \n                    arXiv:1812.08008\n                    \n                   (2018)","DOI":"10.1109\/CVPR.2017.143"},{"issue":"12","key":"20_CR6","doi-asserted-by":"publisher","first-page":"3941","DOI":"10.1007\/s00521-016-2294-8","volume":"28","author":"O Oyedotun","year":"2017","unstructured":"Oyedotun, O., Khashman, A.: Deep learning in vision-based static hand gesture recognition. Neural Comput. Appl. 28(12), 3941\u20133951 (2017)","journal-title":"Neural Comput. Appl."},{"key":"20_CR7","unstructured":"Zhu, Y., Lan, Z., Newsam, S., Hauptmann, A.G.: Hidden two-stream convolutional networks for action recognition. arXiv preprint \n                    arXiv:1704.00389\n                    \n                   (2017)"},{"key":"20_CR8","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.patrec.2018.05.009","volume":"117","author":"D Ouyang","year":"2019","unstructured":"Ouyang, D., Zhang, Y., Shao, J.: Video-based person re-identification via spatio-temporal attentional and two-stream fusion convolutional networks. Pattern Recogn. Lett. 117, 153\u2013160 (2019)","journal-title":"Pattern Recogn. Lett."},{"key":"20_CR9","unstructured":"Li, Z., Gavves, E., Jain, M., Snoek, C.G.: VideoLSTM convolves, attends and flows for action recognition. arXiv preprint \n                    arXiv:1607.01794\n                    \n                   (2016)"},{"key":"20_CR10","doi-asserted-by":"crossref","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"20_CR11","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2010","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35, 221\u2013231 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR12","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.patcog.2017.05.025","volume":"71","author":"L Nanni","year":"2017","unstructured":"Nanni, L., Ghidoni, S., Brahnam, S.: Handcrafted vs non-handcrafted features for computer vision classification. Pattern Recogn. 71, 158\u2013172 (2017)","journal-title":"Pattern Recogn."},{"issue":"3","key":"20_CR13","first-page":"27","volume":"2","author":"C Chang","year":"2011","unstructured":"Chang, C., Lin, C.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. TIST 2(3), 27 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol. TIST"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Remilekun Basaru, R., Slabaugh, G., Alonso, E., Child, C.: Hand pose estimation using deep stereovision and markov-chain monte carlo. In Proceedings of the IEEE International Conference on Computer Vision, pp. 595\u2013603 (2017)","DOI":"10.1109\/ICCVW.2017.76"},{"key":"20_CR15","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-981-13-3185-5_6","volume-title":"Innovations in Soft Computing and Information Technology","author":"K Sinha","year":"2019","unstructured":"Sinha, K., Kumari, R., Priya, A., Paul, P.: A computer vision-based gesture recognition using hidden markov model. In: Chattopadhyay, J., Singh, R., Bhattacherjee, V. (eds.) Innovations in Soft Computing and Information Technology, pp. 55\u201367. Springer, Singapore (2019). \n                    https:\/\/doi.org\/10.1007\/978-981-13-3185-5_6"},{"key":"20_CR16","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097\u20131105 (2012)"},{"key":"20_CR17","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.patcog.2018.02.011","volume":"80","author":"J Tang","year":"2018","unstructured":"Tang, J., Cheng, H., Zhao, Y., Guo, H.: Structured dynamic time warping for continuous hand trajectory gesture recognition. Pattern Recogn. 80, 21\u201331 (2018)","journal-title":"Pattern Recogn."},{"key":"20_CR18","doi-asserted-by":"publisher","first-page":"23713","DOI":"10.1109\/ACCESS.2018.2887223","volume":"7","author":"G Li","year":"2019","unstructured":"Li, G., Wu, H., Jiang, G., Xu, S., Liu, H.: Dynamic gesture recognition in the Internet of Things. IEEE Access 7, 23713\u201323724 (2019)","journal-title":"IEEE Access"},{"issue":"8","key":"20_CR19","doi-asserted-by":"publisher","first-page":"2202","DOI":"10.1016\/j.patcog.2013.01.033","volume":"46","author":"S Priyal","year":"2013","unstructured":"Priyal, S., Bora, P.: A robust static hand gesture recognition system using geometry based normalizations and Krawtchouk moments. Pattern Recogn. 46(8), 2202\u20132219 (2013)","journal-title":"Pattern Recogn."},{"issue":"12","key":"20_CR20","doi-asserted-by":"publisher","first-page":"2171","DOI":"10.3390\/s16122171","volume":"16","author":"J Lin","year":"2016","unstructured":"Lin, J., Ruan, X., Yu, N., Yang, Y.: Adaptive local spatiotemporal features from RGB-D data for one-shot learning gesture recognition. Sensors 16(12), 2171 (2016)","journal-title":"Sensors"},{"key":"20_CR21","doi-asserted-by":"crossref","unstructured":"Wan, J., Zhao, Y., Zhou, S., Guyon, I., Escalera, S., Li, S.: Chalearn looking at people RGB-D isolated and continuous datasets for gesture recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 56\u201364 (2016)","DOI":"10.1109\/CVPRW.2016.100"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Speed\/accuracy trade-offs for modern convolutional object detectors. In: Proceedings of 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR-2017, pp. 3296\u20133297 (2017)","DOI":"10.1109\/CVPR.2017.351"},{"issue":"1","key":"20_CR24","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1109\/TPAMI.2017.2781233","volume":"41","author":"R Ranjan","year":"2019","unstructured":"Ranjan, R., Patel, V., Chellappa, R.: Hyperface: a deep multi-task learning framework for face detection, landmark localization, pose estimation, and gender recognition. IEEE Trans. Pattern Anal. Mach. Intell. 41(1), 121\u2013135 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"20_CR25","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1007\/s11263-016-0957-7","volume":"126","author":"L Pigou","year":"2018","unstructured":"Pigou, L., Van Den Oord, A., Dieleman, S., Van Herreweghe, M., Dambre, J.: Beyond temporal pooling: recurrence and temporal convolutions for gesture recognition in video. Int. J. Comput. Vis. 126, 430\u2013439 (2018)","journal-title":"Int. J. Comput. Vis."},{"key":"20_CR26","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, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Escalante, H., et al.: ChaLearn joint contest on multimedia challenges beyond visual analysis: an overview. In: 23rd International Conference on Pattern Recognition, ICPR-2016, pp. 67\u201373 (2016)","DOI":"10.1109\/ICPR.2016.7899609"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Zhu, G., Zhang, L., Mei, L., Shao, J., Song, J., Shen, P.: Large-scale isolated gesture recognition using pyramidal 3D convolutional networks. In 23rd International Conference on Pattern Recognition, ICPR-2016, pp. 19\u201324 (2016)","DOI":"10.1109\/ICPR.2016.7899601"},{"key":"20_CR29","unstructured":"Duan, J., Zhou, S., Wan, J., Guo, X., Li, S.: Multi-modality fusion based on consensus-voting and 3D convolution for isolated gesture recognition. arXiv preprint \n                    arXiv:1611.06689\n                    \n                   (2016)"},{"issue":"1","key":"20_CR30","first-page":"21","volume":"14","author":"J Duan","year":"2018","unstructured":"Duan, J., Wan, J., Zhou, S., Guo, X., Li, S.: A unified framework for multi-modal isolated gesture recognition. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 14(1), 21 (2018)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl. (TOMM)"},{"key":"20_CR31","unstructured":"Kudubayeva, S., Ryumin, D., Kalghanov, M.: The influence of the kazakh language semantic peculiarities on computer sign language. In: International Conferences on Information and Communication Technology, Society, and Human Beings, ICT-2016, Madeira, Portugal, pp. 221\u2013226 (2016)"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Karpov, A., Kipyatkova, I., Zelezny, M.: Automatic technologies for processing spoken sign languages. In: 5th Workshop on Spoken Language Technologies for Under-Resourced Languages, SLTU-2016, vol. 81, pp. 201\u2013207 (2016)","DOI":"10.1016\/j.procs.2016.04.050"},{"key":"20_CR33","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, W., Liu, S., Gao, Z., Tang, C., Ogunbona, P.: Large-scale isolated gesture recognition using convolutional neural networks. In: Proceedings of the 23rd International Conference on Pattern Recognition, ICPR-2016, pp. 7\u201312 (2016)","DOI":"10.1109\/ICPR.2016.7899599"},{"issue":"1","key":"20_CR34","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1006\/cviu.1998.0716","volume":"73","author":"D Gavrila","year":"1999","unstructured":"Gavrila, D.: The visual analysis of human movement: a survey. Comput. vis. Image Underst. 73(1), 2\u201398 (1999)","journal-title":"Comput. vis. Image Underst."},{"key":"20_CR35","unstructured":"Abadi, M., et al.: TensorFlow: a system for large-scale machine learning. In: 12th Symposium on Operating Systems Design and Implementation, pp. 265\u2013283 (2016)"},{"key":"20_CR36","unstructured":"Gulli, A., Pal, S.: Deep Learning with Keras. Packt Publishing Ltd (2017)"},{"key":"20_CR37","unstructured":"Liu, L., Shao, L.: Learning discriminative representations from RGB-D video data. In: Twenty-Third International Joint Conference on Artificial Intelligence (2013)"},{"key":"20_CR38","doi-asserted-by":"crossref","unstructured":"Tung, P., Ngoc, L.: Elliptical density shape model for hand gesture recognition. In: International Proceedings of the ICTD (2014)","DOI":"10.1145\/2676585.2676600"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Yang, X., Gupta, S., Kim, K., Tyree, S., Kautz, J.: Online detection and classification of dynamic hand gestures with recurrent 3D convolutional neural network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4207\u20134215 (2016)","DOI":"10.1109\/CVPR.2016.456"},{"key":"20_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-016-3988-8","volume-title":"Multimedia Tools and Applications","author":"J Zheng","year":"2016","unstructured":"Zheng, J., Feng, Z., Xu, C., Hu, J., Ge, W.: Fusing shape and spatiotemporal features for depth-based dynamic hand gesture recognition. In: Zheng, J., Feng, Z., Xu, C., Hu, J., Ge, W. (eds.) Multimedia Tools and Applications, vol. 76, pp. 1\u201320. Springer, New York (2016). \n                    https:\/\/doi.org\/10.1007\/s11042-016-3988-8"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-26061-3_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T19:06:51Z","timestamp":1565291211000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-26061-3_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030260606","9783030260613"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-26061-3_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"24 July 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Istanbul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turkey","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"86","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":"57","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":"66% - 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)"}}]}}