{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T16:45:32Z","timestamp":1773333932870,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1109\/clei67442.2025.11420649","type":"proceedings-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T19:35:56Z","timestamp":1773257756000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Spatio-Temporal Sign Recognition with Multiscale Vision Transformers and Multimodal Fusion"],"prefix":"10.1109","author":[{"given":"Graziela S.","family":"Ara\u00fajo","sequence":"first","affiliation":[{"name":"Federal University of Ouro Preto,Postgraduate Program in Computer Science,Ouro Preto,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luana","family":"Isabel Gon\u00e7alvez de Lima","sequence":"additional","affiliation":[{"name":"Federal University of Viçosa,Interdisciplinary Unit for Inclusive Policies,Viçosa,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberta B.","family":"Oliveira","sequence":"additional","affiliation":[{"name":"University of Brasilia,Department of Computer Science,Brasilia,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillermo","family":"C\u00e1mara-Ch\u00e1vez","sequence":"additional","affiliation":[{"name":"Federal University of Ouro Preto,Department of Computer Science,Ouro Preto,Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCAI61061.2024.10602025"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE62371.2024.10760810"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-022-01341-4"},{"key":"ref4","volume-title":"L\u00edngua de sinais brasileira: estudos ling\u00fc\u00edsticos","author":"De Quadros","year":"2009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114179"},{"key":"ref6","article-title":"Self-supervised video transformers for isolated sign language recognition","author":"Sandoval-Castaneda","year":"2023"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.01004","article-title":"Sign language transformers: Joint end-to-end sign language recognition and translation","author":"Camgoz","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.11606\/d.100.2016.tde-20122015-212746"},{"key":"ref9","first-page":"6018","article-title":"Sign language recognition with transformer networks","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference","author":"De Coster"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW54805.2022.00024"},{"key":"ref11","first-page":"6824","article-title":"Multiscale vision transformers","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Fan"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/rs15092393"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119394"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LifeTech53646.2022.9754851"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00612-w"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSPA55860.2022.10019112"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICIVC58118.2023.10270259"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICSPCRE62303.2024.10674996"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2015.7177428"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2021.05.071"},{"key":"ref22","article-title":"Vision transformer: What it is & how it works [2024 guide]","author":"Shah","year":"2022"},{"key":"ref23","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref24","first-page":"12 116","article-title":"Do vision transformers see like convolutional neural networks?","volume":"34","author":"Raghu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14732-3"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18681-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-14646-0"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/INDICON59947.2023.10440818"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref30","article-title":"Multiscale vision transformers: An architecture for modeling visual data","year":"2021"},{"key":"ref31","volume-title":"Review \u2014 MViT: Multiscale vision transformers","author":"Tsang","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01781"},{"key":"ref34","article-title":"Torchvision: Pytorch\u2019s computer vision library","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3358851"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00052"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2018.8363769"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000290"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.measen.2022.100385"}],"event":{"name":"2025 LI Latin American Computer Conference (CLEI)","location":"Valpara\u00edso, Chile","start":{"date-parts":[[2025,10,27]]},"end":{"date-parts":[[2025,10,31]]}},"container-title":["2025 LI Latin American Computer Conference (CLEI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11420220\/11420231\/11420649.pdf?arnumber=11420649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T04:50:37Z","timestamp":1773291037000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11420649\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/clei67442.2025.11420649","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]}}}