The notion of Usage Control (UCON) has been introduced recently to extend traditional access controls by including three decision factors called authorizations, obligations, and co...
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 ...
System theoretic approaches to action recognition model the dynamics of a scene with linear dynamical systems (LDSs) and perform classification using metrics on the space of LDSs, ...
Rizwan Chaudhry, Avinash Ravichandran, Gregory D. ...
We address the problem of learning view-invariant 3D models of human motion from motion capture data, in order to recognize human actions from a monocular video sequence with arbi...
An automatic human shape-motion analysis method based on a fusion architecture is proposed for human action recognition in videos. Robust shape-motion features are extracted from h...