2 papers
cs.CV2025
Learning with Category-Equivariant Architectures for Human Activity Recognition
Yoshihiro Maruyama
We propose CatEquiv, a category-equivariant neural network for Human Activity Recognition (HAR) from inertial sensors that systematically encodes temporal, amplitude, and structura…
cs.LG2025
Learning with Category-Equivariant Representations for Human Activity Recognition
Yoshihiro Maruyama
Human activity recognition is challenging because sensor signals shift with context, motion, and environment; effective models must therefore remain stable as the world around them…