Self-supervised learning with a contrastive VideoMoCo framework for Saudi Arabic sign language recognition using 3D convolutional networks

Abstract Saudi Arabic Sign Language (SArSL) recognition poses significant challenges due to its complex spatio-temporal structure and the scarcity of annotated datasets. This paper introduces a self-supervised learning framework built upon the Video Momentum Contrast (VideoMoCo) paradigm integrated...

Disgrifiad llawn

Manylion Llyfryddiaeth

Prif Awduron:	Mahmoud Rokaya, Dalia I. Hemdan, Mohammed A. Alzain, Ibrahim Gad, El-Sayed Atlam
Fformat:	Artigo
Iaith:	Inglês
Cyhoeddwyd:	Nature Portfolio 2025-11-01
Cyfres:	Scientific Reports
Pynciau:	Arabic sign language recognition VideoMoCo Self-Supervised learning 3D convolutional neural networks Contrastive learning Saudi arabic sign language (ArSL)
Mynediad Ar-lein:	https://doi.org/10.1038/s41598-025-23494-x
Tagiau:	Ychwanegu Tag Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!