Towards the extraction of robust sign embeddings for low resource sign language recognition

M De Coster, E Rushe, R Holmes, A Ventresque… - arxiv preprint arxiv …, 2023 - arxiv.org
Isolated Sign Language Recognition (SLR) has mostly been applied on datasets containing
signs executed slowly and clearly by a limited group of signers. In real-world scenarios …

From scarcity to understanding: transfer learning for the extremely low resource irish sign language

R Holmes, E Rushe, M De Coster… - Proceedings of the …, 2023 - openaccess.thecvf.com
One of the most significant challenges to sign language recognition (SLR) today is the low
resource nature of sign language datasets, with many datasets being extremely low …

Translating Spanish into Spanish Sign Language: Combining rules and data-driven approaches

L Chiruzzo, E McGill, SE Gómez… - Proceedings of the fifth …, 2022 - aclanthology.org
This paper presents a series of experiments on translating between spoken Spanish and
Spanish Sign Language glosses (LSE), including enriching Neural Machine Translation …

Metamorphic Testing for Pose Estimation Systems

M Duran, T Laurent, E Rushe, A Ventresque - arxiv preprint arxiv …, 2025 - arxiv.org
Pose estimation systems are used in a variety of fields, from sports analytics to livestock
care. Given their potential impact, it is paramount to systematically test their behaviour and …

The Key Points: Using Feature Importance to Identify Shortcomings in Sign Language Recognition Models

RM Holmes, E Rushe, A Ventresque - Proceedings of the 2024 …, 2024 - aclanthology.org
Pose estimation keypoints are widely used in sign language recognition (SLR) as a means
of generalising to unseen signers. Despite the advantages of keypoints, SLR models …

[PDF][PDF] Skeleton-based ethiopian sign language recognition using deep learning

D Kuma, M Meshesha - 2023 - ir.haramaya.edu.et
Recent reports show that there are over 1.5 billion people around the globe with hearing
impairment, and here in Ethiopia, their number is estimated to be over 1.2 million. These …