{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T23:00:45Z","timestamp":1794438045419,"version":"4.9.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:00:00Z","timestamp":1780444800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:00:00Z","timestamp":1786579200000},"content-version":"vor","delay-in-days":71,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-53835-3","type":"journal-article","created":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T08:53:24Z","timestamp":1780476804000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Transformer-based word level Bangla sign language recognition using relative quantization encoding"],"prefix":"10.1038","volume":"16","author":[{"given":"Husne Ara","family":"Rubaiyeat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Njayou","family":"Youssouf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Kamrul","family":"Hasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hasan","family":"Mahmud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,3]]},"reference":[{"key":"53835_CR1","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit,J., Jones,L., Gomez, A.N., Kaiser,\u0141. & Polosukhin,I. Attention is all you need. In Proc. Advances in Neural Information Processing Systems (NeurIPS), pp. 5998\u20136008 (2017)."},{"key":"53835_CR2","doi-asserted-by":"publisher","unstructured":"Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. In Proc. Int. Conf. Learning Representations (ICLR). https:\/\/doi.org\/10.48550\/arXiv.1409.0473 (2015).","DOI":"10.48550\/arXiv.1409.0473"},{"key":"53835_CR3","doi-asserted-by":"publisher","unstructured":"Li, D., Rodriguez-Opazo, C., Yu X., & Li, H. Word-level deep sign language recognition from video: A new large-scale dataset and methods comparison. In 2020 IEEE Winter Conf. Applications of Computer Vision (WACV), 1448\u20131458, https:\/\/doi.org\/10.1109\/WACV45572.2020.9093512 (2019).","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"53835_CR4","doi-asserted-by":"publisher","first-page":"181340","DOI":"10.1109\/ACCESS.2020.3028072","volume":"8","author":"O Sincan","year":"2020","unstructured":"Sincan O.M. and Keles H. Y.,\u00a0\"AUTSL: A Large Scale Multi-Modal Turkish Sign Language Dataset and Baseline Methods,\" in IEEE Access (2020), vol. 8, pp. 181340\u2013181355, 2020.https:\/\/doi.org\/10.1109\/ACCESS.2020.3028072","journal-title":"IEEE Access"},{"key":"53835_CR5","doi-asserted-by":"publisher","unstructured":"Kapitanov, A., Karina, K., Nagaev, A., Elizaveta, P. Slovo: Russian sign language dataset. In Christensen, H.I., Corke, P., Detry, R., Weibel, JB., Vincze, M. (eds.) Computer Vision Systems. ICVS 2023, Lecture Notes in Computer Science, Vol. 14253 (Springer, 2023). https:\/\/doi.org\/10.1007\/978-3-031-44137-0_6.","DOI":"10.1007\/978-3-031-44137-0_6"},{"issue":"1","key":"53835_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3423420","volume":"20","author":"AAI Sidig","year":"2021","unstructured":"Sidig, A. A. I., Luqman, H., Mahmoud, S. & Mohandes, M. KArSL: Arabic sign language database. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 20(1), 1\u201319. https:\/\/doi.org\/10.1145\/3423420 (2021).","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"53835_CR7","doi-asserted-by":"publisher","first-page":"59612","DOI":"10.1109\/ACCESS.2021.3069714","volume":"9","author":"MA Bencherif","year":"2021","unstructured":"Bencherif, M.A., Algabri, M., Mekhtiche, M.A., Faisal, M., Alsulaiman, M., Mathkour, H., Al-hammadi, M., & Ghaleb, H. (2021). Arabic Sign Language Recognition System Using 2D Hands and Body Skeleton Data. IEEE Access, 9, 59612-59627.","journal-title":"IEEE Access"},{"key":"53835_CR8","doi-asserted-by":"crossref","unstructured":"Imashev, A., M. Mukushev, V. Kimmelman & A. Sandygulova (2020). A Dataset for Linguistic Understanding, Visual Evaluation, and Recognition of Sign Languages: The K-RSL. In Proceedings of the 24th Conference on Computational Natural Language Learning, 631-640. Online: Association for Computational Linguistics. https:\/\/www.aclweb.org\/anthology\/2020.conll-1.51","DOI":"10.18653\/v1\/2020.conll-1.51"},{"key":"53835_CR9","unstructured":"Kagirov, I., Ivanko, D., Ryumin, D., Axyonov, A., & Karpov, A. TheRuSLan: Database of russian sign language. In Proc. Twelfth Language Resources and Evaluation Conference, pp. 6079\u20136085. https:\/\/aclanthology.org\/2020.lrec-1.746.pdf (2020)."},{"key":"53835_CR10","volume-title":"Devisign: dataset and evaluation for 3D sign language recognition","author":"X Chai","year":"2015","unstructured":"Chai, X., Wang, H., Yin, F., Zhao, Z., Chu, J., Chang, X., Zhou, D., Li, X., Zhou, M., Chen, X.: DEVISIGN: Dataset and evaluation for 3D sign language recognition. Technical Report VIPL-TR-14-03, Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences (2015)"},{"issue":"9","key":"53835_CR11","doi-asserted-by":"publisher","first-page":"2822","DOI":"10.1109\/TCSVT.2018.2870740","volume":"29","author":"J Huang","year":"2019","unstructured":"Huang, J., Zhou, W., Li, H., Li, W.: Attention-based 3D-CNNs for large-vocabulary sign language recognition. IEEE Trans. Circuits Syst. Video Technol. 29(9), 2822\u20132832 (2019). https:\/\/doi.org\/10.1109\/TCSVT.2018.2870740","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"53835_CR12","doi-asserted-by":"publisher","unstructured":"Sams, A., Akash, AH., & Rahman, SMM. SignBD-Word: Video-based bangla word-level sign language and pose translation. In 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), Delhi, India, pp. 1\u20137 (2023). https:\/\/doi.org\/10.1109\/ICCCNT56998.2023.10306914.","DOI":"10.1109\/ICCCNT56998.2023.10306914"},{"issue":"34","key":"53835_CR13","doi-asserted-by":"publisher","first-page":"42399","DOI":"10.1007\/s11042-025-20792-4","volume":"84","author":"HA Rubaiyeat","year":"2025","unstructured":"Rubaiyeat, H. A., Mahmud, H., Habib, A. & Hasan, M. K. BdSLW60: A word-level Bangla sign language dataset. Multimedia Tools Appl. 84(34), 42399\u201342423. https:\/\/doi.org\/10.1007\/s11042-025-20792-4 (2025).","journal-title":"Multimedia Tools Appl."},{"key":"53835_CR14","doi-asserted-by":"publisher","unstructured":"Bohacek,T., Zemcik,P., Kanis, J. Sign pose-based transformer for word-level sign language recognition. In Proc. IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), pp. 182\u2013191 (2022). https:\/\/doi.org\/10.1109\/WACVW54805.2022.00024","DOI":"10.1109\/WACVW54805.2022.00024"},{"key":"53835_CR15","doi-asserted-by":"publisher","unstructured":"Sridhar, A., Ganesan, R. G., Kumar,P., Khapra,M. M. INCLUDE: A large scale dataset for indian sign language recognition. In Proc. 28th ACM International Conference on Multimedia (ACM MM), pp. 1366\u20131375, https:\/\/doi.org\/10.1145\/3394171.3413528 (2020).","DOI":"10.1145\/3394171.3413528"},{"key":"53835_CR16","doi-asserted-by":"publisher","unstructured":"Camgoz,N. C., Koller,O., Hadfield, S., Bowden, R. Sign language transformers: Joint end-to-end sign language recognition and translation. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10023\u201310033, https:\/\/doi.org\/10.1109\/CVPR42600.2020.01004 (2020).","DOI":"10.1109\/CVPR42600.2020.01004"},{"key":"53835_CR17","doi-asserted-by":"publisher","unstructured":"Lugaresi,C. et al., MediaPipe: A framework for building perception pipelines. Preprint at arXiv:1906.08172, https:\/\/doi.org\/10.48550\/arXiv.1906.08172 (2019).","DOI":"10.48550\/arXiv.1906.08172"},{"key":"53835_CR18","doi-asserted-by":"publisher","unstructured":"Cao, Z., Simon, T., Wei, S.-E. & Sheikh, Y. Realtime multi-person 2d pose estimation using part affinity fields. Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 7291\u20137299. https:\/\/doi.org\/10.1109\/CVPR.2017.143 (2017).","DOI":"10.1109\/CVPR.2017.143"},{"key":"53835_CR19","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.1007\/s00371-022-02762-1","volume":"40","author":"H Mahmud","year":"2024","unstructured":"Mahmud, H., Morshed, M. & Hasan, M. K. Quantized depth image and skeleton-based dynamic hand gesture recognition. Visual Comput. 40, 1432\u20132315. https:\/\/doi.org\/10.1007\/s00371-022-02762-1 (2024).","journal-title":"Visual Comput."},{"issue":"9","key":"53835_CR20","doi-asserted-by":"publisher","first-page":"5830","DOI":"10.1109\/TSMC.2019.2957347","volume":"51","author":"PM Ferreira","year":"2021","unstructured":"Ferreira, P. M., Pernes, D., Rebelo, A. & Cardoso, J. S. DeSIRe: Deep signer-invariant representations for sign language recognition. IEEE Trans. Syst. Man Cybern. Syst. 51(9), 5830\u20135845. https:\/\/doi.org\/10.1109\/TSMC.2019.2957347 (2021).","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"53835_CR21","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1007\/BF00410640","volume":"4","author":"M Wertheimer","year":"1923","unstructured":"Wertheimer, M. Laws of Organization in Perceptual Forms. Psychol. Res. 4, 301\u2013350.https:\/\/doi.org\/10.1037\/11496-005 (1923).","journal-title":"Psychol. Res."},{"key":"53835_CR22","volume-title":"The Design of Everyday Things","author":"DA Norman","year":"1988","unstructured":"Norman, D. A. The Design of Everyday Things (Basic Books, 1988)."},{"key":"53835_CR23","doi-asserted-by":"publisher","unstructured":"Molchanov, P. et al. Online detection and classification of dynamic hand gestures with recurrent 3D convolutional neural networks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 4207\u20134215, https:\/\/doi.org\/10.1109\/CVPR.2016.456 (2016).","DOI":"10.1109\/CVPR.2016.456"},{"key":"53835_CR24","doi-asserted-by":"publisher","unstructured":"Bragg, D. et al. Sign language recognition, generation, and translation: An interdisciplinary perspective. In Proc. 21st International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS), pp. 16\u201331 https:\/\/doi.org\/10.1145\/3308561.3353774 (2019).","DOI":"10.1145\/3308561.3353774"},{"key":"53835_CR25","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1007\/s00371-021-02229-9","volume":"38","author":"S Zeghoud","year":"2022","unstructured":"Zeghoud, S., Ali, S. G. & Ertugrul, E. Real-time spatial normalization for dynamic gesture classification. Visual Comput. 38, 1345\u20131357. https:\/\/doi.org\/10.1007\/s00371-021-02229-9 (2022).","journal-title":"Visual Comput."},{"key":"53835_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.1406.2199","volume":"27","author":"K Simonyan","year":"2014","unstructured":"Simonyan, K. & Zisserman, A. Two-stream convolutional networks for action recognition in videos. Adv. Neural Inf. Process. Syst. 27, 1,https:\/\/doi.org\/10.48550\/arXiv.1406.2199 (2014).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"53835_CR27","doi-asserted-by":"publisher","unstructured":"Graves,A., Fern\u00e1ndez, S., Gomez, F.,& Schmidhuber, J. Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks. In Proc. 23rd International Conference on Machine Learning (ICML), pp. 369\u2013376, https:\/\/doi.org\/10.1145\/1143844.1143891 (2006).","DOI":"10.1145\/1143844.1143891"},{"key":"53835_CR28","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1109\/WACVW54805.2022.00024","volume":"2022","author":"M Boh\u00e1\u010dek","year":"2022","unstructured":"Boh\u00e1\u010dek, M. & Hr\u00faz, M. Sign Pose-based transformer for word-level sign language recognition. IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) 2022, 182\u2013191, https:\/\/doi.org\/10.1109\/WACVW54805.2022.00024 (2022).","journal-title":"IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)"},{"key":"53835_CR29","doi-asserted-by":"publisher","unstructured":"B. Huang, Z. Zhang, G. Zhan, Y. Qin, and L. Wang, MGMAE: Motion guided masking for video masked autoencoding. In Proc. IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France, pp. 13447\u201313458, https:\/\/doi.org\/10.1109\/ICCV51070.2023.01241 (2023).","DOI":"10.1109\/ICCV51070.2023.01241"},{"key":"53835_CR30","doi-asserted-by":"publisher","unstructured":"Arnab,A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M. & Schmid, C. ViViT: A video vision transformer. In Proc. IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada, pp. 6836\u20136846, https:\/\/doi.org\/10.1109\/ICCV48922.2021.00676 (2021).","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"53835_CR31","doi-asserted-by":"publisher","unstructured":"Bertasius, G., Wang, H., & Torresani, L. Is Space-time attention all you need for video understanding? In Proc. 38th International Conference on Machine Learning (ICML), Proc. Machine Learning Research, vol. 139, pp. 813\u2013824, https:\/\/doi.org\/10.48550\/arXiv.2102.05095 (2021).","DOI":"10.48550\/arXiv.2102.05095"},{"key":"53835_CR32","doi-asserted-by":"publisher","unstructured":"Athitsos, V., Neidle, C., Sclaroff, S., Nash, J.P., Stefan, A., Yuan, Q., & Thangali, A. The American Sign Language Lexicon Video Dataset. 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 1-8.  https:\/\/doi.org\/10.1109\/CVPRW.2008.4563181 (2008)","DOI":"10.1109\/CVPRW.2008.4563181"},{"key":"53835_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115657","volume":"182","author":"S Sharma","year":"2021","unstructured":"Sharma, S. & Singh, S. Vision-based hand gesture recognition using deep learning for the interpretation of sign language. Expert Syst. Appl. 182, 115657. https:\/\/doi.org\/10.1016\/j.eswa.2021.115657 (2021).","journal-title":"Expert Syst. Appl."},{"key":"53835_CR34","doi-asserted-by":"publisher","unstructured":"Simonyan, K., & Zisserman, A. Very deep convolutional networks for large-scale image recognition. In Proc. Int. Conf. Learning Representations (ICLR), https:\/\/doi.org\/10.48550\/arXiv.1409.1556 (2015).","DOI":"10.48550\/arXiv.1409.1556"},{"issue":"20","key":"53835_CR35","doi-asserted-by":"publisher","first-page":"58329","DOI":"10.1007\/s11042-023-17361-y","volume":"83","author":"G Khartheesvar","year":"2024","unstructured":"Khartheesvar, G., Kumar, M., Yadav, A. K. & Yadav, D. Automatic Indian sign language recognition using MediaPipe holistic and LSTM network. Multimedia Tools Appl. 83(20), 58329\u201358348. https:\/\/doi.org\/10.1007\/s11042-023-17361-y (2024).","journal-title":"Multimedia Tools Appl."},{"key":"53835_CR36","unstructured":"Google, MediaPipe holistic: Simultaneous face, hand, and pose prediction on device, Google AI Blog. https:\/\/ai.googleblog.com\/2020\/08\/on-device-real-time-body-pose-tracking.html (2020)."},{"issue":"1","key":"53835_CR37","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","volume":"43","author":"Z Cao","year":"2021","unstructured":"Cao, Z., Hidalgo, G., Simon, T., Wei, S.-E. & Sheikh, Y. OpenPose: Realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans. Pattern Anal. Mach. Intell. 43(1), 172\u2013186. https:\/\/doi.org\/10.1109\/TPAMI.2019.2929257 (2021).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"53835_CR38","volume-title":"Cognitive Psychology and Its Implications","author":"JR Anderson","year":"2015","unstructured":"Anderson, J. R. Cognitive Psychology and Its Implications 8th edn. (Worth Publishers, 2015).","edition":"8"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53835-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53835-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53835-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,13]],"date-time":"2026-08-13T00:26:27Z","timestamp":1786580787000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-53835-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,3]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["53835"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-53835-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7091875\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,3]]},"assertion":[{"value":"10 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The methods and procedures that involved human participants in this study were carried out with relevant guidelines and protocols, including ethical standards established by the Department of Research, Extension, Advisory Services and Publications (REASP) of Islamic University of Technology (IUT). This research study has received ethical approval from REASP, IUT, with ethics approval no. 2024\/02.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Informed consent was obtained from all participants involved in this study. Each participant voluntarily agreed to provide sign language samples after being informed about the research objectives, procedures, potential risks, and their rights.","order":3,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"25259"}}