LA-Sign achieves state-of-the-art skeleton-based sign language recognition on WLASL and MSASL by using recurrent looped transformers with adaptive hyperbolic geometry alignment.
Nature Reviews Methods Primers4(1), 82 (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
EOMC shows that chaotic systems like Lorenz-96 and tokamak turbulence are best captured as metastable switches between persistent low-dimensional manifolds with slowly decreasing exit times.
citing papers explorer
-
LA-Sign: Looped Transformers with Geometry-aware Alignment for Skeleton-based Sign Language Recognition
LA-Sign achieves state-of-the-art skeleton-based sign language recognition on WLASL and MSASL by using recurrent looped transformers with adaptive hyperbolic geometry alignment.
-
Linearly-scalable and entropy-optimal learning of nonstationary and nonlinear manifolds
EOMC shows that chaotic systems like Lorenz-96 and tokamak turbulence are best captured as metastable switches between persistent low-dimensional manifolds with slowly decreasing exit times.
- Conditional Attribution for Root Cause Analysis in Time-Series Anomaly Detection