Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
Human activity recognition is a challenging task, especially
when its background is unknown or changing,
and when scale or illumination differs in each video.
Approaches utilizi...
We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditi...
This paper explores a recently proposed and rarely reported subspace learning method, Spectral Regression Discriminant Analysis (SRDA) [1, 2], on silhouette based human action rec...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...