{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T20:04:13Z","timestamp":1773777853300,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T00:00:00Z","timestamp":1768608000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T00:00:00Z","timestamp":1768953600000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Minufiya University"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Intell Syst"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Arabic Sign Language (ArSL) is an important medium of communication for hearing and deaf communities. Recognition of ArSL is difficult, especially in signer-independent systems. Mostly studies deal with ArSL recognition from images or videos and dependent on the signers. To simulate the real world, we must introduce ArSL recognition models based on videos with independent signers to recognize signature style diversity. This paper introduced an ArSL-TGRU model to recognize Arabic sign language from videos using a hybrid transformer and Gated Recurrent Unit (GRU). Four sequential transformer layers improve temporal and spatial abstraction, while two simultaneous GRU modules capture sequential dynamics. To capture complex dynamic movements, this network reduces overfitting and models long-range relationships via attention techniques and regularization. The proposed model applied on a custom dataset extracted from KArSL\u2019s. The custom dataset contains 60,918 videos for 136 signs, divided into 6 categories of signs (letters, numbers, words-family, words-feeling, words-job, and sentences) by three independent signers. From the experiments, the proposed model outperformed six common architectures in several categories with different signers. The proposed model\u2019s ability to understand spatial and temporal connections, adapt to signer variances, and achieve robust generalization across various linguistic forms.<\/jats:p>","DOI":"10.1007\/s44196-025-01120-y","type":"journal-article","created":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T05:45:15Z","timestamp":1768628715000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ArSL-TGRU: A Hybrid Model for Signer-Independent Arabic Sign Language Recognition from Videos Based on Transformer and GRU"],"prefix":"10.1007","volume":"19","author":[{"given":"Mohammed M.","family":"Nasef","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aya","family":"El-Sayed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eman M.","family":"AbouNassar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,17]]},"reference":[{"issue":"6","key":"1120_CR1","doi-asserted-by":"publisher","DOI":"10.3390\/math13060909","volume":"13","author":"Y Said","year":"2025","unstructured":"Said, Y., Boubaker, S., Altowaijri, S.M., Alsheikhy, A.A., Atri, M.: Adaptive transformer-based deep learning framework for continuous sign language recognition and translation. Mathematics 13(6), 909 (2025). https:\/\/doi.org\/10.3390\/math13060909","journal-title":"Mathematics"},{"key":"1120_CR2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2021.0120380","author":"RA Alawwad","year":"2021","unstructured":"Alawwad, R.A., Bchir, O., Maher, M.: Arabic sign language recognition using faster R-CNN. IJACSA (2021). https:\/\/doi.org\/10.14569\/IJACSA.2021.0120380","journal-title":"IJACSA"},{"key":"1120_CR3","doi-asserted-by":"publisher","unstructured":"Huang, C.L., Tsai, B.L.: A Vision-Based Taiwanese Sign Language recognition. In: 2010 20th International Conference on Pattern Recognition, Istanbul, Turkey: IEEE, Aug. 2010, pp. 3683\u20133686. https:\/\/doi.org\/10.1109\/ICPR.2010.1110","DOI":"10.1109\/ICPR.2010.1110"},{"key":"1120_CR4","doi-asserted-by":"publisher","first-page":"83199","DOI":"10.1109\/ACCESS.2020.2990699","volume":"8","author":"S Aly","year":"2020","unstructured":"Aly, S., Aly, W.: DeepArSLR: a novel signer-independent deep learning framework for isolated Arabic sign language gestures recognition. IEEE Access 8, 83199\u201383212 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2990699","journal-title":"IEEE Access"},{"key":"1120_CR5","doi-asserted-by":"publisher","unstructured":"Ismail, M.H., Dawwd, S.A., Ali, F.H.: Arabic sign language detection using deep learning based pose estimation. In: 2021 2nd Information Technology To Enhance e-learning and Other Application (IT-ELA), Baghdad, Iraq: IEEE, Dec. 2021, pp. 161\u2013166. https:\/\/doi.org\/10.1109\/IT-ELA52201.2021.9773404","DOI":"10.1109\/IT-ELA52201.2021.9773404"},{"key":"1120_CR6","unstructured":"google-ai-edge\/mediapipe. (Aug. 24, 2025). C++. google-ai-edge. Accessed: Aug. 24, 2025. [Online]. Available: https:\/\/github.com\/google-ai-edge\/mediapipe"},{"issue":"07","key":"1120_CR7","doi-asserted-by":"publisher","first-page":"13009","DOI":"10.1609\/aaai.v34i07.7001","volume":"34","author":"H Zhou","year":"2020","unstructured":"Zhou, H., Zhou, W., Zhou, Y., Li, H.: Spatial-temporal multi-cue network for continuous sign language recognition. AAAI 34(07), 13009\u201313016 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.7001","journal-title":"AAAI"},{"key":"1120_CR8","doi-asserted-by":"publisher","unstructured":"Assaleh, K., Shanableh, T., Fanaswala, M., Bajaj, H., Amin, F.: Vision-based system for continuous Arabic Sign Language recognition in user dependent mode. In: 2008 5th International Symposium on Mechatronics and Its Applications, Amman: IEEE, May 2008, pp. 1\u20135. https:\/\/doi.org\/10.1109\/ISMA.2008.4648841","DOI":"10.1109\/ISMA.2008.4648841"},{"issue":"4","key":"1120_CR9","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1016\/j.dsp.2011.01.015","volume":"21","author":"T Shanableh","year":"2011","unstructured":"Shanableh, T., Assaleh, K.: User-independent recognition of Arabic sign language for facilitating communication with the deaf community. Digit. Signal Process. 21(4), 535\u2013542 (2011). https:\/\/doi.org\/10.1016\/j.dsp.2011.01.015","journal-title":"Digit. Signal Process."},{"key":"1120_CR10","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1016\/j.procs.2022.12.066","volume":"215","author":"B Sundar","year":"2022","unstructured":"Sundar, B., Bagyammal, T.: American sign language recognition for alphabets using MediaPipe and LSTM. Procedia Comput. Sci. 215, 642\u2013651 (2022). https:\/\/doi.org\/10.1016\/j.procs.2022.12.066","journal-title":"Procedia Comput. Sci."},{"issue":"8","key":"1120_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2023.101642","volume":"35","author":"M Alsulaiman","year":"2023","unstructured":"Alsulaiman, M., et al.: Facilitating the communication with deaf people: building a largest Saudi sign language dataset. J. King Saud Univ. - Comput. Inf. Sci. 35(8), 101642 (2023). https:\/\/doi.org\/10.1016\/j.jksuci.2023.101642","journal-title":"J. King Saud Univ. - Comput. Inf. Sci."},{"key":"1120_CR12","doi-asserted-by":"publisher","first-page":"192527","DOI":"10.1109\/ACCESS.2020.3032140","volume":"8","author":"M Al-Hammadi","year":"2020","unstructured":"Al-Hammadi, M., et al.: Deep learning-based approach for sign language gesture recognition with efficient hand gesture representation. IEEE Access 8, 192527\u2013192542 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.3032140","journal-title":"IEEE Access"},{"issue":"19","key":"1120_CR13","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11193228","volume":"11","author":"GH Samaan","year":"2022","unstructured":"Samaan, G.H., et al.: MediaPipe\u2019s landmarks with RNN for dynamic sign language recognition. Electronics 11(19), 3228 (2022). https:\/\/doi.org\/10.3390\/electronics11193228","journal-title":"Electronics"},{"issue":"6","key":"1120_CR14","doi-asserted-by":"publisher","DOI":"10.3390\/computers13060153","volume":"13","author":"RS Abdul Ameer","year":"2024","unstructured":"Abdul Ameer, R.S., Ahmed, M.A., Al-Qaysi, Z.T., Salih, M.M., Shuwandy, M.L.: Empowering communication: a deep learning framework for Arabic sign language recognition with an attention mechanism. Computers 13(6), 153 (2024). https:\/\/doi.org\/10.3390\/computers13060153","journal-title":"Computers"},{"key":"1120_CR15","doi-asserted-by":"publisher","unstructured":"Oulad-Naoui, S., Ben-Abderrahmane, H., Chagha, A., Cherif, A.: An LSTM-based system for dynamic arabic sign language recognition. In: Presented at the International Conference on Emerging Intelligent Systems for Sustainable Development (ICEIS 2024), Atlantis Press, Aug. 2024, pp. 313\u2013323. https:\/\/doi.org\/10.2991\/978-94-6463-496-9_24","DOI":"10.2991\/978-94-6463-496-9_24"},{"key":"1120_CR16","doi-asserted-by":"publisher","first-page":"160728","DOI":"10.1109\/ACCESS.2024.3485131","volume":"12","author":"M Almaazmi","year":"2024","unstructured":"Almaazmi, M., Elkadi, S., Elsayed, L., Salman, L., Shanableh, T.: Motion images with positioning information and deep learning for continuous Arabic sign language recognition in signer dependent and independent modes. IEEE Access 12, 160728\u2013160740 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3485131","journal-title":"IEEE Access"},{"issue":"11","key":"1120_CR17","doi-asserted-by":"publisher","DOI":"10.3390\/s24113683","volume":"24","author":"TH Noor","year":"2024","unstructured":"Noor, T.H., et al.: Real-time Arabic sign language recognition using a hybrid deep learning model. Sensors 24(11), 3683 (2024). https:\/\/doi.org\/10.3390\/s24113683","journal-title":"Sensors"},{"issue":"9","key":"1120_CR18","doi-asserted-by":"publisher","DOI":"10.3390\/s25092916","volume":"25","author":"N Algethami","year":"2025","unstructured":"Algethami, N., Farhud, R., Alghamdi, M., Almutairi, H., Sorani, M., Aleisa, N.: Continuous Arabic sign language recognition models. Sensors 25(9), 2916 (2025). https:\/\/doi.org\/10.3390\/s25092916","journal-title":"Sensors"},{"key":"1120_CR19","doi-asserted-by":"publisher","unstructured":"Suliman, W., Deriche, M., Luqman, H., Mohandes, M.: Arabic sign language recognition using deep machine learning. In: 2021 4th International Symposium on Advanced Electrical and Communication Technologies (ISAECT), Alkhobar, Saudi Arabia: IEEE, Dec. 2021, pp. 1\u20134. https:\/\/doi.org\/10.1109\/ISAECT53699.2021.9668405","DOI":"10.1109\/ISAECT53699.2021.9668405"},{"issue":"1","key":"1120_CR20","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 (2021). https:\/\/doi.org\/10.1145\/3423420","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"issue":"1","key":"1120_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3584984","volume":"23","author":"S Alyami","year":"2024","unstructured":"Alyami, S., Luqman, H., Hammoudeh, M.: Isolated Arabic sign language recognition using a transformer-based model and landmark keypoints. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 23(1), 1\u201319 (2024). https:\/\/doi.org\/10.1145\/3584984","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"issue":"1","key":"1120_CR22","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3390\/s23010002","volume":"23","author":"MS Abdallah","year":"2022","unstructured":"Abdallah, M.S., Samaan, G.H., Wadie, A.R., Makhmudov, F., Cho, Y.-I.: Light-weight deep learning techniques with advanced processing for real-time hand gesture recognition. Sensors 23(1), 2 (2022). https:\/\/doi.org\/10.3390\/s23010002","journal-title":"Sensors"},{"key":"1120_CR23","unstructured":"Abdallah and fuzhao, M.: DSL-46 Dataset-20221030T133143Z-001.zip. Oct. 2022, Accessed: Oct. 14, 2025. [Online]. Available: https:\/\/osf.io\/yxmnt"},{"key":"1120_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107395","volume":"95","author":"W Abdul","year":"2021","unstructured":"Abdul, W., et al.: Intelligent real-time Arabic sign language classification using attention-based inception and BiLSTM. Comput. Electr. Eng. 95, 107395 (2021). https:\/\/doi.org\/10.1016\/j.compeleceng.2021.107395","journal-title":"Comput. Electr. Eng."},{"key":"1120_CR25","doi-asserted-by":"publisher","first-page":"79491","DOI":"10.1109\/ACCESS.2020.2990434","volume":"8","author":"M Al-Hammadi","year":"2020","unstructured":"Al-Hammadi, M., Muhammad, G., Abdul, W., Alsulaiman, M., Bencherif, M.A., Mekhtiche, M.A.: Hand gesture recognition for sign language using 3DCNN. IEEE Access 8, 79491\u201379509 (2020). https:\/\/doi.org\/10.1109\/ACCESS.2020.2990434","journal-title":"IEEE Access"},{"issue":"5","key":"1120_CR26","doi-asserted-by":"publisher","first-page":"6807","DOI":"10.1007\/s11042-022-13423-9","volume":"82","author":"MM Balaha","year":"2023","unstructured":"Balaha, M.M., et al.: A vision-based deep learning approach for independent-users Arabic sign language interpretation. Multimed. Tools Appl. 82(5), 6807\u20136826 (2023). https:\/\/doi.org\/10.1007\/s11042-022-13423-9","journal-title":"Multimed. Tools Appl."},{"key":"1120_CR27","doi-asserted-by":"publisher","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. Dec. 03, 2012, arXiv: arXiv:1212.0402. https:\/\/doi.org\/10.48550\/arXiv.1212.0402","DOI":"10.48550\/arXiv.1212.0402"},{"key":"1120_CR28","doi-asserted-by":"publisher","first-page":"145929","DOI":"10.1109\/ACCESS.2021.3122921","volume":"9","author":"N Aloysius","year":"2021","unstructured":"Aloysius, N., M, G., Nedungadi, P.: Incorporating relative position information in transformer-based sign language recognition and translation. IEEE Access 9, 145929\u2013145942 (2021). https:\/\/doi.org\/10.1109\/ACCESS.2021.3122921","journal-title":"IEEE Access"},{"issue":"5","key":"1120_CR29","doi-asserted-by":"publisher","DOI":"10.3390\/app13053029","volume":"13","author":"J Shin","year":"2023","unstructured":"Shin, J., et al.: Korean Sign Language recognition using transformer-based deep neural network. Appl. Sci. 13(5), 3029 (2023). https:\/\/doi.org\/10.3390\/app13053029","journal-title":"Appl. Sci."},{"issue":"1","key":"1120_CR30","doi-asserted-by":"publisher","first-page":"301","DOI":"10.32604\/jai.2024.054314","volume":"6","author":"FM Shiri","year":"2024","unstructured":"Shiri, F.M., Perumal, T., Mustapha, N., Mohamed, R.: A comprehensive overview and comparative analysis on deep learning models: CNN, RNN, LSTM, GRU. JAI 6(1), 301\u2013360 (2024). https:\/\/doi.org\/10.32604\/jai.2024.054314","journal-title":"JAI"},{"key":"1120_CR31","doi-asserted-by":"publisher","unstructured":"Powers, D,M,W,: Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. Oct. 11, 2020, arXiv: arXiv:2010.16061. https:\/\/doi.org\/10.48550\/arXiv.2010.16061","DOI":"10.48550\/arXiv.2010.16061"},{"issue":"21","key":"1120_CR32","doi-asserted-by":"publisher","DOI":"10.3390\/app132111625","volume":"13","author":"NM Alharthi","year":"2023","unstructured":"Alharthi, N.M., Alzahrani, S.M.: Vision transformers and transfer learning approaches for Arabic Sign Language recognition. Appl. Sci. 13(21), 11625 (2023). https:\/\/doi.org\/10.3390\/app132111625","journal-title":"Appl. Sci."},{"issue":"1","key":"1120_CR33","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/4567989","volume":"2022","author":"M Zakariah","year":"2022","unstructured":"Zakariah, M., Alotaibi, Y.A., Koundal, D., Guo, Y., Mamun Elahi, M.: Sign language recognition for Arabic alphabets using transfer learning technique. Comput. Intell. Neurosci. 2022(1), 4567989 (2022). https:\/\/doi.org\/10.1155\/2022\/4567989","journal-title":"Comput. Intell. Neurosci."},{"key":"1120_CR34","doi-asserted-by":"publisher","unstructured":"Tanaka, Y., Oka, K., Ono, T., Inoue, K.: Accuracy analysis of machine learning-based performance modeling for microprocessors. In: 2016 Fourth International Japan-Egypt Conference on Electronics, Communications and Computers (JEC-ECC), May 2016, pp. 83\u201386. https:\/\/doi.org\/10.1109\/JEC-ECC.2016.7518973","DOI":"10.1109\/JEC-ECC.2016.7518973"},{"key":"1120_CR35","doi-asserted-by":"publisher","unstructured":"Gordon-Rodriguez, E., Loaiza-Ganem, G., Pleiss, G., Cunningham, J.P.: Uses and Abuses of the Cross-Entropy Loss: Case Studies in Modern Deep Learning. Nov. 10, 2020, arXiv: arXiv:2011.05231. https:\/\/doi.org\/10.48550\/arXiv.2011.05231","DOI":"10.48550\/arXiv.2011.05231"}],"container-title":["International Journal of Computational Intelligence Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44196-025-01120-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44196-025-01120-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44196-025-01120-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T17:01:23Z","timestamp":1773766883000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44196-025-01120-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,17]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1120"],"URL":"https:\/\/doi.org\/10.1007\/s44196-025-01120-y","relation":{},"ISSN":["1875-6883"],"issn-type":[{"value":"1875-6883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,17]]},"assertion":[{"value":"21 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 January 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 March 2026","order":7,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":8,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"In Table 1 of the PDF version, the Arabic characters were displayed in reverse and therefore appeared visually incorrect","order":9,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interest"}},{"value":"No experiments involving humans or animals in this article.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"All authors gave their consent.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"40"}}