Masa: Motion-aware masked autoencoder with semantic alignment for sign language recognition

W Zhao, H Hu, W Zhou, Y Mao… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Sign language recognition (SLR) has long been plagued by insufficient model
representation capabilities. Although current pre-training approaches have alleviated this …

Self-supervised representation learning with spatial-temporal consistency for sign language recognition

W Zhao, W Zhou, H Hu, M Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Recently, there have been efforts to improve the performance in sign language recognition
by designing self-supervised learning methods. However, these methods capture limited …

Modelling the distribution of human motion for sign language assessment

O Cory, OM Sincan, M Vowels, A Battisti… - arxiv preprint arxiv …, 2024 - arxiv.org
Sign Language Assessment (SLA) tools are useful to aid in language learning and are
underdeveloped. Previous work has focused on isolated signs or comparison against a …