Sign Language Processing (SLP) provides a foundation for a more inclusive future in language technology; however, the field faces several significant challenges that must be addressed to achieve practical, real-world applications. This work addresses multi-view isolated sign recognition (MV-ISR), and highlights the essential role of 3D awareness and geometry in SLP systems. We introduce the NGT200 dataset, a novel spatio-temporal multi-view benchmark, establishing MV-ISR as distinct from single-view ISR (SV-ISR). We demonstrate the benefits of synthetic data and propose conditioning sign representations on spatial symmetries inherent in sign language. Leveraging an SE(2) equivariant model improves MV-ISR performance by 8%-22% over the baseline.
@article{arxiv.2409.15284,
title = {The NGT200 Dataset: Geometric Multi-View Isolated Sign Recognition},
author = {Oline Ranum and David R. Wessels and Gomer Otterspeer and Erik J. Bekkers and Floris Roelofsen and Jari I. Andersen},
journal= {arXiv preprint arXiv:2409.15284},
year = {2024}
}
Comments
Proceedings of the Geometry-grounded Representation Learning and Generative Modeling Workshop (GRaM) at the 41 st International Conference on Machine Learning, Vienna, Austria. PMLR 251, 2024