{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:47:56Z","timestamp":1762559276892,"version":"build-2065373602"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:00:00Z","timestamp":1762560000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Computing"],"DOI":"10.1007\/s10791-025-09772-2","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:43:07Z","timestamp":1762558987000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced sign language translation using three stream multimodal occlusion resilient transformer"],"prefix":"10.1007","volume":"28","author":[{"given":"Rina","family":"Damdoo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Praveen","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,8]]},"reference":[{"key":"9772_CR1","unstructured":"Way A. Sign Language Machine Translation. Machine Translation: Technologies and Applications. Springer. https:\/\/books.google.co.in\/books?id=nWIwEQAAQBAJ"},{"key":"9772_CR2","first-page":"2","volume":"1","author":"M Kakde","year":"2016","unstructured":"Kakde M, Nakrani M, Rawate A. A review paper on sign language recognition system for deaf and dumb people using image processing. Int J Eng Res. 2016;1:2.","journal-title":"Int J Eng Res"},{"key":"9772_CR3","doi-asserted-by":"crossref","unstructured":"Koller O, Zargaran S, Ney H. Re-sign: Re-aligned end-to-end sequence modelling with deep recurrent cnn-hmms. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3416\u20133424 (2017)","DOI":"10.1109\/CVPR.2017.364"},{"key":"9772_CR4","unstructured":"Saunders B, Camg\u00f6z NC, Bowden R. Progressive transformers for end-to-end sign language production. CoRR abs\/2004.14874 (2020) https:\/\/arxiv.org\/abs\/2004.148742004.14874"},{"issue":"5","key":"9772_CR5","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1080\/02564602.2014.961576","volume":"31","author":"S Joudaki","year":"2014","unstructured":"Joudaki S, Mohamad D, Saba T, Rehman A, Al-Rodhaan M, Al-Dhelaan A. Vision-based sign language classification: A directional review. IETE Tech Revi. 2014;31(5):383\u201391. https:\/\/doi.org\/10.1080\/02564602.2014.961576.","journal-title":"IETE Tech Revi"},{"key":"9772_CR6","doi-asserted-by":"publisher","unstructured":"Camgoz NC, Hadfield S, Koller O, Ney H, Bowden R. Neural sign language translation. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7784\u20137793 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00812","DOI":"10.1109\/CVPR.2018.00812"},{"key":"9772_CR7","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I. Attention is all you need. CoRR abs\/1706.03762 (2017) https:\/\/arxiv.org\/abs\/1706.037621706.03762"},{"key":"9772_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103799","volume":"235","author":"H Wang","year":"2023","unstructured":"Wang H, Zhang L, Fan H, Luo T. Collaborative three-stream transformers for video captioning. Comput Vision Image Underst. 2023;235:103799. https:\/\/doi.org\/10.1016\/j.cviu.2023.103799.","journal-title":"Comput Vision Image Underst"},{"key":"9772_CR9","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.neucom.2021.04.072","volume":"456","author":"N Liu","year":"2021","unstructured":"Liu N, Sun X, Yu H, Zhang W, Xu G. D-mmt: A concise decoder-only multi-modal transformer for abstractive summarization in videos. Neurocomputing. 2021;456:179\u201389. https:\/\/doi.org\/10.1016\/j.neucom.2021.04.072.","journal-title":"Neurocomputing"},{"key":"9772_CR10","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.neucom.2022.09.099","volume":"512","author":"S Xiao","year":"2022","unstructured":"Xiao S, Wang S, Huang Z, Wang Y, Jiang H. Two-stream transformer network for sensor-based human activity recognition. Neurocomputing. 2022;512:253\u201368. https:\/\/doi.org\/10.1016\/j.neucom.2022.09.099.","journal-title":"Neurocomputing"},{"key":"9772_CR11","first-page":"1","volume":"20","author":"Y Liu","year":"2023","unstructured":"Liu Y, Cui G, Luo J, Yao L, Chang X. Two-stream multi-level dynamic point transformer for two-person interaction recognition. ACM Trans Multimed Comput Commun Appl. 2023;20:1\u201322.","journal-title":"ACM Trans Multimed Comput Commun Appl"},{"key":"9772_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101904","volume":"100","author":"K Hu","year":"2023","unstructured":"Hu K, Li L, Tao X, Vel\u00e1squez JD, Delaney P. Information fusion in crime event analysis: A decade survey on data, features and models. Inf Fusion. 2023;100:101904. https:\/\/doi.org\/10.1016\/j.inffus.2023.101904.","journal-title":"Inf Fusion"},{"key":"9772_CR13","unstructured":"Pulapakura R. Multimodal Models and Fusion: A Complete Guide. Accessed: 2025-01-16 (2023). https:\/\/medium.com\/@raj.pulapakura\/multimodal-models-and-fusion-a-complete-guide-225ca91f6861"},{"key":"9772_CR14","unstructured":"Chen Y, Zuo R, Wei F, Wu Y, Liu S, Mak B. Two-Stream Network for Sign Language Recognition and Translation (2023). https:\/\/arxiv.org\/abs\/2211.01367"},{"key":"9772_CR15","doi-asserted-by":"publisher","unstructured":"Ren J, Shen X, Lin Z, M?ch R. Best frame selection in a short video. In: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 3201\u20133210 (2020). https:\/\/doi.org\/10.1109\/WACV45572.2020.9093615","DOI":"10.1109\/WACV45572.2020.9093615"},{"key":"9772_CR16","doi-asserted-by":"publisher","first-page":"145929","DOI":"10.1109\/ACCESS.2021.3122921","volume":"9","author":"N Aloysius","year":"2021","unstructured":"Aloysius N, Geetha M, Nedungadi P. Incorporating relative position information in transformer-based sign language recognition and translation. IEEE Access. 2021;9:145929\u201342.","journal-title":"IEEE Access"},{"issue":"1","key":"9772_CR17","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/s10791-025-09509-1","volume":"28","author":"R Damdoo","year":"2025","unstructured":"Damdoo R, Kumar P. Signedgelvm transformer model for enhanced sign language translation on edge devices. Discov Comput. 2025;28(1):15. https:\/\/doi.org\/10.1007\/s10791-025-09509-1.","journal-title":"Discov Comput"},{"key":"9772_CR18","doi-asserted-by":"publisher","unstructured":"Yue F, Ko T. An investigation of positional encoding in transformer-based end-to-end speech recognition. In: 2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 1\u20135 (2021). https:\/\/doi.org\/10.1109\/ISCSLP49672.2021.9362093","DOI":"10.1109\/ISCSLP49672.2021.9362093"},{"key":"9772_CR19","unstructured":"Camgoz NC, Koller O, Hadfield S, Bowden R. Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation (2020). https:\/\/arxiv.org\/abs\/2003.13830"},{"key":"9772_CR20","doi-asserted-by":"crossref","unstructured":"Zhou H, Zhou W-g, Qi W, Pu J, Li H. Improving sign language translation with monolingual data by sign back-translation. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 1316\u20131325 (2021)","DOI":"10.1109\/CVPR46437.2021.00137"},{"key":"9772_CR21","doi-asserted-by":"crossref","unstructured":"Chen Y, Wei F, Sun X, Wu Z, Lin S. A simple multi-modality transfer learning baseline for sign language translation. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 5110\u20135120 (2022)","DOI":"10.1109\/CVPR52688.2022.00506"},{"key":"9772_CR22","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.cola.2019.04.002","volume":"52","author":"S Ravi","year":"2019","unstructured":"Ravi S, Suman M, Kishore PVV, Kumar E K, Kumar M TK, Kumar D A. Multi modal spatio temporal co-trained cnns with single modal testing on rgb-d based sign language gesture recognition. J Comput Lang. 2019;52:88\u2013102. https:\/\/doi.org\/10.1016\/j.cola.2019.04.002.","journal-title":"J Comput Lang"},{"key":"9772_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-023-14548-1","volume":"82","author":"G Prasath","year":"2023","unstructured":"Prasath G, Kumarappan A. Prediction of sign language recognition based on multi layered cnn. Multimed Tools Appl. 2023;82:1\u201321. https:\/\/doi.org\/10.1007\/s11042-023-14548-1.","journal-title":"Multimed Tools Appl"},{"key":"9772_CR24","first-page":"17043","volume":"35","author":"Y Chen","year":"2022","unstructured":"Chen Y. Two-stream network for sign language recognition and translation. Adv Neural Inf Process Syst. 2022;35:17043\u201356.","journal-title":"Adv Neural Inf Process Syst"},{"issue":"7","key":"9772_CR25","doi-asserted-by":"publisher","first-page":"7205","DOI":"10.1007\/s12652-020-02396-y","volume":"12","author":"R Elakkiya","year":"2021","unstructured":"Elakkiya R. Machine learning based sign language recognition: a review and its research frontier. J Ambient Intell Human Comput. 2021;12(7):7205\u201324. https:\/\/doi.org\/10.1007\/s12652-020-02396-y.","journal-title":"J Ambient Intell Human Comput"},{"key":"9772_CR26","doi-asserted-by":"publisher","unstructured":"Fish E, Weinbren J, Gilbert A. Two-stream transformer architecture for long video understanding. In: British Machine Vision Conference (2022). https:\/\/doi.org\/10.48550\/arXiv.2208.01753 . https:\/\/api.semanticscholar.org\/CorpusID:251280242","DOI":"10.48550\/arXiv.2208.01753"},{"key":"9772_CR27","unstructured":"Zhou H, Zhou W, Zhou Y, Li H. Spatial-temporal multi-cue network for continuous sign language recognition. CoRR abs\/2002.03187 (2020) https:\/\/arxiv.org\/abs\/2002.031872002.03187"},{"key":"9772_CR28","unstructured":"Coster MD, D\u2019Oosterlinck K, Pizurica M, Rabaey P, Verlinden S, Herreweghe MV, Dambre J. Frozen pretrained transformers for neural sign language translation. In: Machine Translation Summit (2021). https:\/\/api.semanticscholar.org\/CorpusID:237010918"},{"key":"9772_CR29","unstructured":"Yin K. Better sign language translation with transformers. CoRR abs\/2004.00588 (2020) https:\/\/arxiv.org\/abs\/2004.005882004.00588"},{"key":"9772_CR30","doi-asserted-by":"crossref","unstructured":"Voskou A, Panousis KP, Kosmopoulos DI, Metaxas DN, Chatzis SP. Stochastic transformer networks with linear competing units: Application to end-to-end sl translation. 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), 11926\u201311935 (2021)","DOI":"10.1109\/ICCV48922.2021.01173"},{"issue":"9","key":"9772_CR31","doi-asserted-by":"publisher","first-page":"11221","DOI":"10.1109\/tpami.2023.3269220","volume":"45","author":"H Hu","year":"2023","unstructured":"Hu H, Zhao W, Zhou W, Li H. Signbert+: Hand-model-aware self-supervised pre-training for sign language understanding. IEEE Trans Pattern Anal Mach Intell. 2023;45(9):11221\u201339. https:\/\/doi.org\/10.1109\/tpami.2023.3269220.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9772_CR32","doi-asserted-by":"crossref","unstructured":"Guan M, Wang Y, Ma G, Liu J, Sun M. Multi-Stream Keypoint Attention Network for Sign Language Recognition and Translation (2024). https:\/\/arxiv.org\/abs\/2405.05672","DOI":"10.1016\/j.patcog.2025.111602"},{"key":"9772_CR33","doi-asserted-by":"crossref","unstructured":"Jiang S, Sun B, Wang L, Bai Y, Li K, Fu YR. Skeleton aware multi-modal sign language recognition. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 3408\u20133418 (2021)","DOI":"10.1109\/CVPRW53098.2021.00380"},{"key":"9772_CR34","unstructured":"Ahn J, Jang Y, Chung JS. SlowFast Network for Continuous Sign Language Recognition (2023). https:\/\/arxiv.org\/abs\/2309.12304"},{"key":"9772_CR35","doi-asserted-by":"publisher","unstructured":"Gan S, Yin Y, Jiang Z, Xia K, Xie L, Lu S. Contrastive learning for sign language recognition and translation, pp. 763\u2013772 (2023). https:\/\/doi.org\/10.24963\/ijcai.2023\/85","DOI":"10.24963\/ijcai.2023\/85"},{"key":"9772_CR36","doi-asserted-by":"publisher","unstructured":"Yin A, Zhao Z, Jin W, Zhang M, Zeng X, He X. Mlslt: Towards multilingual sign language translation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5099\u20135109 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00505","DOI":"10.1109\/CVPR52688.2022.00505"},{"key":"9772_CR37","doi-asserted-by":"publisher","unstructured":"Ham S, Park K, Jang Y, Oh Y, Yun S, Yoon S, Kim CJ, Park H-M, Kweon IS. Ksl-guide: A large-scale korean sign language dataset including interrogative sentences for guiding the deaf and hard-of-hearing. In: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021), pp. 1\u20138 (2021). https:\/\/doi.org\/10.1109\/FG52635.2021.9667011","DOI":"10.1109\/FG52635.2021.9667011"},{"key":"9772_CR38","unstructured":"LISN: Mediapi-RGB. ORTOLANG (Open Resources and TOols for LANGuage) \u2013www.ortolang.fr (2024). https:\/\/hdl.handle.net\/11403\/mediapi-rgb\/v1"},{"key":"9772_CR39","unstructured":"Duarte AC, Palaskar S, Ghadiyaram D, DeHaan K, Metze F, Torres J, Gir\u00f3-i-Nieto X. How2sign: A large-scale multimodal dataset for continuous american sign language. CoRR abs\/2008.08143 (2020) https:\/\/arxiv.org\/abs\/2008.081432008.08143"},{"key":"9772_CR40","doi-asserted-by":"publisher","unstructured":"Koller O, Ney H, Bowden R. Deep hand: How to train a cnn on 1 million hand images when your data is continuous and weakly labelled. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3793\u20133802 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.412","DOI":"10.1109\/CVPR.2016.412"},{"key":"9772_CR41","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 abs\/2006.10214 (2020)"},{"key":"9772_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2021.103055","volume":"76","author":"L Song","year":"2021","unstructured":"Song L, Yu G, Yuan J, Liu Z. Human pose estimation and its application to action recognition: A survey. J Visual Commun Image Represent. 2021;76:103055. https:\/\/doi.org\/10.1016\/j.jvcir.2021.103055.","journal-title":"J Visual Commun Image Represent"},{"key":"9772_CR43","doi-asserted-by":"publisher","first-page":"2662","DOI":"10.1109\/TMM.2021.3087006","volume":"24","author":"J Zhao","year":"2022","unstructured":"Zhao J, Qi W, Zhou W, Duan N, Zhou M, Li H. Conditional sentence generation and cross-modal reranking for sign language translation. IEEE Transact Multimed. 2022;24:2662\u201372. https:\/\/doi.org\/10.1109\/TMM.2021.3087006.","journal-title":"IEEE Transact Multimed"},{"key":"9772_CR44","unstructured":"Kim Y, Kwak M, Lee D, Kim Y, Baek H. Keypoint based Sign Language Translation without Glosses (2022). https:\/\/arxiv.org\/abs\/2204.10511"},{"key":"9772_CR45","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A. Automatic differentiation in pytorch. In: NIPS 2017 Workshop on Autodiff (2017). https:\/\/openreview.net\/forum?id=BJJsrmfCZ"},{"key":"9772_CR46","doi-asserted-by":"crossref","unstructured":"Papineni K, Roukos S, Ward T, Zhu W-J. Bleu: a method for automatic evaluation of machine translation. In: Annual Meeting of the Association for Computational Linguistics (2002). https:\/\/api.semanticscholar.org\/CorpusID:11080756","DOI":"10.3115\/1073083.1073135"},{"key":"9772_CR47","unstructured":"Lin C-Y. Rouge: A package for automatic evaluation of summaries. In: Annual Meeting of the Association for Computational Linguistics (2004). https:\/\/api.semanticscholar.org\/CorpusID:964287"},{"key":"9772_CR48","doi-asserted-by":"publisher","unstructured":"Li N, Xue B, Ma L, Zhang M. Automatic fuzzy architecture design for defect detection via classifier-assisted multiobjective optimization approach. IEEE Transactions on Evolutionary Computation, 1\u20131 (2025) https:\/\/doi.org\/10.1109\/TEVC.2025.3530416","DOI":"10.1109\/TEVC.2025.3530416"}],"container-title":["Discover Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-025-09772-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-025-09772-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-025-09772-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:43:11Z","timestamp":1762558991000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-025-09772-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,8]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["9772"],"URL":"https:\/\/doi.org\/10.1007\/s10791-025-09772-2","relation":{},"ISSN":["2948-2992"],"issn-type":[{"value":"2948-2992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,8]]},"assertion":[{"value":"1 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"not applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"260"}}