{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T04:08:17Z","timestamp":1778213297560,"version":"3.51.4"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korean Government","award":["RS-2024-00435623"],"award-info":[{"award-number":["RS-2024-00435623"]}]},{"name":"Core Research Institute Basic Science Research Program"},{"name":"Ministry of Education","award":["2018R1A6A1A03025242"],"award-info":[{"award-number":["2018R1A6A1A03025242"]}]},{"name":"Competitive Research Fund of The University of Aizu"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Open J. Comput. Soc."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ojcs.2026.3682330","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:49:23Z","timestamp":1775764163000},"page":"706-717","source":"Crossref","is-referenced-by-count":1,"title":["Stack Transformer-Based Spatial-Temporal Attention Model for Dynamic Sign Language and Fingerspelling Recognition"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0007-4435","authenticated-orcid":false,"given":"Koki","family":"Hirooka","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1238-0464","authenticated-orcid":false,"given":"Abu Saleh Musa","family":"Miah","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9761-3870","authenticated-orcid":false,"given":"Tatsuya","family":"Murakami","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2966-7055","authenticated-orcid":false,"given":"Md. Al Mehedi","family":"Hasan","sequence":"additional","affiliation":[{"name":"Department of Computer Science &amp; Engineering, Rajshahi University of Engineering &amp; Technology, Rajshahi, Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8375-2456","authenticated-orcid":false,"given":"Yong Seok","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Electronics Engineering, Kwangwoon University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7476-2468","authenticated-orcid":false,"given":"Jungpil","family":"Shin","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deafness and hearing loss","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093512"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321502"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01090"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3269220"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.619"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130290"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nbt1206-1565"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"ref16","first-page":"1","article-title":"Sign language recognition using partial least squares and RGB-D information","volume-title":"Proc. IX Workshop de Visao Computacional","author":"Estrela","year":"2013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2014.110"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2014.20"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.12197"},{"key":"ref20","first-page":"255","article-title":"Convolutional networks for images, speech, and time series","volume-title":"The Handbook of Brain Theory and Neural Networks","author":"LeCun","year":"1998"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.9781\/ijimai.2019.09.002"},{"key":"ref22","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. 3rd Int. Conf. Learn. Representations (ICLR)","author":"Simonyan","year":"2015"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICSCET.2018.8537248"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"issue":"8","key":"ref25","article-title":"BenSignNet: Bengali sign language alphabet recognition using concatenated segmentation and convolutional neural network","volume-title":"Appl. Sci.","volume":"12","author":"Miah","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/GHTC46095.2019.9033031"},{"key":"ref27","article-title":"KU-BdSL: Khulna university bengali sign language dataset","author":"Shorif","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICBSLP.2018.8554466"},{"issue":"17","key":"ref29","article-title":"American sign language alphabet recognition by extracting feature from hand pose estimation","volume-title":"Sensors","volume":"21","author":"Shin","year":"2021"},{"key":"ref30","article-title":"Mediapipe hands: On-device real-time hand tracking","volume-title":"Proc. CVPR Workshop Comput. Vis. AR\/VR","author":"Vakunov","year":"2020"},{"key":"ref31","first-page":"3149","article-title":"LightGBM: A highly efficient gradient boosting decision tree","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Ke","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3399839"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177428"},{"key":"ref34","article-title":"MS-ASL: A large-scale data set and benchmark for understanding american sign language","volume-title":"Proc. Brit. Mach. Vis. Conf. (BMVC)","author":"Joze","year":"2019"},{"issue":"13","key":"ref35","article-title":"Multi-stream general and graph-based deep neural networks for skeleton-based sign language recognition","volume-title":"Electronics","volume":"12","author":"Miah","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-025-01529-3"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25470"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01430"},{"key":"ref39","article-title":"Uni-Sign: Toward unified sign language understanding at scale","volume-title":"Proc. 13th Int. Conf. Learn. Representations (ICLR)","author":"Li","year":"2025"},{"key":"ref40","first-page":"10524","article-title":"On layer normalization in the transformer architecture","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiong","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.192"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref43","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"issue":"5","key":"ref44","article-title":"Sign2Pose: A pose-based approach for gloss prediction using a transformer model","volume-title":"Sensors","volume":"23","author":"Eunice","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3700878"},{"key":"ref46","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_23"},{"key":"ref48","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations (ICLR)","author":"Loshchilov","year":"2019"},{"key":"ref49","first-page":"10","article-title":"Ubiscription: Finger gesture recognition using smartphone","volume-title":"Proc. IPSJ Interact.","author":"Ikuno","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.133"},{"key":"ref51","article-title":"Classification of japanese signed character with pose estimation and machine learning","author":"Kobayashi","year":"2019"},{"issue":"3","key":"ref52","article-title":"Dynamic japanese sign language recognition throw hand pose estimation using effective feature extraction and classification approach","volume-title":"Sensors","volume":"24","author":"Kakizaki","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3399839"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3372425"}],"container-title":["IEEE Open Journal of the Computer Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8782664\/11319293\/11478319.pdf?arnumber=11478319","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T19:43:26Z","timestamp":1778096606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11478319\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/ojcs.2026.3682330","relation":{},"ISSN":["2644-1268"],"issn-type":[{"value":"2644-1268","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}