{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T15:20:47Z","timestamp":1777130447958,"version":"3.51.4"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T00:00:00Z","timestamp":1717113600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T00:00:00Z","timestamp":1717113600000},"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":["Machine Vision and Applications"],"published-print":{"date-parts":[[2024,7]]},"DOI":"10.1007\/s00138-024-01557-9","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T20:20:27Z","timestamp":1717186827000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Deep multimodal-based finger spelling recognition for Thai sign language: a new benchmark and model composition"],"prefix":"10.1007","volume":"35","author":[{"given":"Wuttichai","family":"Vijitkunsawat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Teeradaj","family":"Racharak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minh","family":"Le\u00a0Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,31]]},"reference":[{"key":"1557_CR1","unstructured":"Organization, W.H.: Deafness and hearing loss. https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/deafness-and-hearing-loss (2023)"},{"key":"1557_CR2","doi-asserted-by":"crossref","unstructured":"Kang, B., Tripathi, S., Nguyen, T.Q.: Real-time sign language fingerspelling recognition using convolutional neural networks from depth map. In: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR), pp. 136\u2013140 (2015). IEEE","DOI":"10.1109\/ACPR.2015.7486481"},{"issue":"1","key":"1557_CR3","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1353\/sls.1996.0012","volume":"92","author":"J Woodward","year":"1996","unstructured":"Woodward, J.: Modern standard Thai sign language, influence from ASL, and its relationship to original Thai sign varieties. Sign Lang. Stud. 92(1), 227\u2013252 (1996)","journal-title":"Sign Lang. Stud."},{"key":"1557_CR4","doi-asserted-by":"crossref","unstructured":"Gattupalli, S., Ghaderi, A., Athitsos, V.: Evaluation of deep learning based pose estimation for sign language recognition. In: Proceedings of the 9th ACM International Conference on PErvasive Technologies Related to Assistive Environments, pp. 1\u20137 (2016)","DOI":"10.1145\/2910674.2910716"},{"key":"1557_CR5","doi-asserted-by":"crossref","unstructured":"Haque, A., Peng, B., Luo, Z., Alahi, A., Yeung, S., Fei-Fei, L.: Towards viewpoint invariant 3d human pose estimation. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp. 160\u2013177 (2016). Springer","DOI":"10.1007\/978-3-319-46448-0_10"},{"key":"1557_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113794","volume":"164","author":"R Rastgoo","year":"2021","unstructured":"Rastgoo, R., Kiani, K., Escalera, S.: Sign language recognition: A deep survey. Expert Syst. Appl. 164, 113794 (2021)","journal-title":"Expert Syst. Appl."},{"key":"1557_CR7","doi-asserted-by":"crossref","unstructured":"Amatanon, V., Chanhang, S., Naiyanetr, P., Thongpang, S.: Sign language-thai alphabet conversion based on electromyogram (emg). In: The 7th 2014 Biomedical Engineering International Conference, pp. 1\u20134 (2014)","DOI":"10.1109\/BMEiCON.2014.7017398"},{"key":"1557_CR8","doi-asserted-by":"crossref","unstructured":"Chansri, C., Srinonchat, J.: Reliability and accuracy of thai sign language recognition with kinect sensor. In: 2016 13th International Conference on Electrical Engineering\/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON), pp. 1\u20134 (2016). IEEE","DOI":"10.1109\/ECTICon.2016.7561403"},{"key":"1557_CR9","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s11265-018-1375-6","volume":"91","author":"P Nakjai","year":"2019","unstructured":"Nakjai, P., Katanyukul, T.: Hand sign recognition for Thai finger spelling: an application of convolution neural network. J. Signal Process. Syst. 91, 131\u2013146 (2019)","journal-title":"J. Signal Process. Syst."},{"key":"1557_CR10","doi-asserted-by":"crossref","unstructured":"Pariwat, T., Seresangtakul, P.: Thai finger-spelling sign language recognition using global and local features with svm. In: 2017 9th International Conference on Knowledge and Smart Technology (KST), pp. 116\u2013120 (2017). IEEE","DOI":"10.1109\/KST.2017.7886111"},{"key":"1557_CR11","doi-asserted-by":"crossref","unstructured":"Silanon, K.: Thai finger-spelling recognition using a cascaded classifier based on histogram of orientation gradient features. Computational intelligence and neuroscience 2017 (2017)","DOI":"10.1155\/2017\/9026375"},{"key":"1557_CR12","unstructured":"Sanalohit, J., Katanyukul, T.: Thai finger spelling recognition: Investigating mediapipe hands potentials. arXiv preprint arXiv:2201.03170 (2022)"},{"issue":"2","key":"1557_CR13","doi-asserted-by":"publisher","first-page":"262","DOI":"10.3390\/sym13020262","volume":"13","author":"T Pariwat","year":"2021","unstructured":"Pariwat, T., Seresangtakul, P.: Multi-stroke Thai finger-spelling sign language recognition system with deep learning. Symmetry 13(2), 262 (2021)","journal-title":"Symmetry"},{"key":"1557_CR14","doi-asserted-by":"crossref","unstructured":"Vijitkunsawat, W., Racharak, T., Nguyen, C., Le\u00a0Minh, N.: Video-based sign language digit recognition for the Thai language: A new dataset and method comparisons (2023)","DOI":"10.5220\/0011643700003411"},{"key":"1557_CR15","doi-asserted-by":"crossref","unstructured":"Vijitkunsawat, W., Racharak, T., Le\u00a0Minh, N.: Deep multimodal-based number finger spelling recognizer for Thai sign language (2023)","DOI":"10.1109\/ISCIT57293.2023.10376072"},{"key":"1557_CR16","doi-asserted-by":"publisher","first-page":"112258","DOI":"10.1109\/ACCESS.2019.2925654","volume":"7","author":"Q Xiao","year":"2019","unstructured":"Xiao, Q., Qin, M., Guo, P., Zhao, Y.: Multimodal fusion based on LSTM and a couple conditional hidden Markov model for Chinese sign language recognition. IEEE Access 7, 112258\u2013112268 (2019)","journal-title":"IEEE Access"},{"key":"1557_CR17","doi-asserted-by":"publisher","first-page":"180270","DOI":"10.1109\/ACCESS.2019.2959206","volume":"7","author":"S Zhang","year":"2019","unstructured":"Zhang, S., Meng, W., Li, H., Cui, X.: Multimodal spatiotemporal networks for sign language recognition. IEEE Access 7, 180270\u2013180280 (2019)","journal-title":"IEEE Access"},{"key":"1557_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, S., Sun, B., Wang, L., Bai, Y., Li, K., Fu, Y.: Skeleton aware multi-modal sign language recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3413\u20133423 (2021)","DOI":"10.1109\/CVPRW53098.2021.00380"},{"issue":"18","key":"1557_CR19","doi-asserted-by":"publisher","first-page":"5151","DOI":"10.3390\/s20185151","volume":"20","author":"JJ Bird","year":"2020","unstructured":"Bird, J.J., Ek\u00e1rt, A., Faria, D.R.: British sign language recognition via late fusion of computer vision and leap motion with transfer learning to american sign language. Sensors 20(18), 5151 (2020)","journal-title":"Sensors"},{"key":"1557_CR20","doi-asserted-by":"crossref","unstructured":"Lin, J., Zeng, A., Wang, H., Zhang, L., Li, Y.: One-stage 3d whole-body mesh recovery with component aware transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21159\u201321168 (2023)","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"1557_CR21","doi-asserted-by":"crossref","unstructured":"Papadimitriou, K., Potamianos, G.: Multimodal sign language recognition via temporal deformable convolutional sequence learning. In: Interspeech, pp. 2752\u20132756 (2020)","DOI":"10.21437\/Interspeech.2020-2691"},{"key":"1557_CR22","doi-asserted-by":"crossref","unstructured":"Li, D., Rodriguez, C., Yu, X., Li, H.: Word-level deep sign language recognition from video: A new large-scale dataset and methods comparison. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1459\u20131469 (2020)","DOI":"10.1109\/WACV45572.2020.9093512"},{"issue":"8","key":"1557_CR23","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(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"1557_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107395","volume":"95","author":"W Abdul","year":"2021","unstructured":"Abdul, W., Alsulaiman, M., Amin, S.U., Faisal, M., Muhammad, G., Albogamy, F.R., Bencherif, M.A., Ghaleb, H.: Intelligent real-time Arabic sign language classification using attention-based inception and Bilstm. Comput. Electr. Eng. 95, 107395 (2021)","journal-title":"Comput. Electr. Eng."},{"key":"1557_CR25","doi-asserted-by":"crossref","unstructured":"Alyami, S., Luqman, H., Hammoudeh, M.: Isolated arabic sign language recognition using a transformer-based model and landmark keypoints. ACM Transactions on Asian and Low-Resource Language Information Processing (2023)","DOI":"10.1145\/3584984"},{"key":"1557_CR26","doi-asserted-by":"publisher","first-page":"22965","DOI":"10.1007\/s11042-020-09048-5","volume":"79","author":"R Rastgoo","year":"2020","unstructured":"Rastgoo, R., Kiani, K., Escalera, S.: Video-based isolated hand sign language recognition using a deep cascaded model. Multimed. Tools Appl. 79, 22965\u201322987 (2020)","journal-title":"Multimed. Tools Appl."},{"key":"1557_CR27","doi-asserted-by":"crossref","unstructured":"Bora, P., Awalgaonkar, T., Palve, H., Joshi, R., Goel, P.: Icodenet-a hierarchical neural network approach for source code identification. In: 13th International Conference on Machine Learning and Computing, pp. 180\u2013185 (2021)","DOI":"10.1145\/3457682.3457709"},{"key":"1557_CR28","unstructured":"Zhang, F., Bazarevsky, V., Vakunov, A., Tkachenka, A., Sung, G., Chang, C.-L., Grundmann, M.: Mediapipe hands: On-device real-time hand tracking. arXiv preprint arXiv:2006.10214 (2020)"},{"key":"1557_CR29","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"1557_CR30","doi-asserted-by":"crossref","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S.W.: Fahad shahbaz khan and mubarak shah. transformers in vision: A survey (2021)","DOI":"10.1145\/3505244"},{"key":"1557_CR31","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"1557_CR32","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"1557_CR33","doi-asserted-by":"crossref","unstructured":"Sleeman, W.C., IV., Kapoor, R., Ghosh, P.: Multimodal classification: Current landscape, taxonomy and future directions. ACM Computing Surveys 55(7), 1\u201331 (2022)","DOI":"10.1145\/3543848"},{"key":"1557_CR34","unstructured":"Thailand, N.A.: Thai Sign Language Posture. https:\/\/www.th-sl.com\/search-by-act\/. Accessed: (Oct 15, 2023) (2023)"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01557-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-024-01557-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-024-01557-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T19:23:01Z","timestamp":1722453781000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-024-01557-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,31]]},"references-count":34,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["1557"],"URL":"https:\/\/doi.org\/10.1007\/s00138-024-01557-9","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,31]]},"assertion":[{"value":"7 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"76"}}