SignGraph: A Sign Sequence is Worth Graphs of Nodes

S Gan, Y Yin, Z Jiang, H Wen… - Proceedings of the …, 2024 - openaccess.thecvf.com
Despite the recent success of sign language research the widely adopted CNN-based
backbones are mainly migrated from other computer vision tasks in which the contours and …

Improving Gloss-free Sign Language Translation by Reducing Representation Density

J Ye, X Wang, W Jiao, J Liang, H Xiong - arXiv preprint arXiv:2405.14312, 2024 - arxiv.org
Gloss-free sign language translation (SLT) aims to develop well-performing SLT systems
with no requirement for the costly gloss annotations, but currently still lags behind gloss …

Adaptive Simultaneous Sign Language Translation with Confident Translation Length Estimation

T Sun, B Fu, C Hu, L Zhang, R Zhang… - Proceedings of the …, 2024 - aclanthology.org
Abstract Traditional non-simultaneous Sign Language Translation (SLT) methods, while
effective for pre-recorded videos, face challenges in real-time scenarios due to inherent …

Trends and challenges for sign language recognition with machine learning

J Fink, M De Coster, J Dambre… - ESANN 2023: 31st …, 2023 - researchportal.unamur.be
Research in natural language processing has led to the creation of powerful tools for
individuals, companies... However, these successes for written languages have not yet …