Much of the existing work on action recognition combines simple features with complex
classifiers or models to represent an action. Parameters of such models usually do not have …

A novel video representation, the layered dynamic texture (LDT), is proposed. The LDT is a
generative model, which represents a video as a collection of stochastic layers of different …

In this chapter, we consider aspects of the crowd that can be modeled holistically, by
analyzing global properties. We first discuss the dynamic texture model for representing …

Automatic human activity analysis from videos is a very important area of research in
computer vision. Of particular interest are the development of a) rich representations for …

This report describes a M. Sc. thesis project in which an exploration study has been
performed to the development of a dynamic model of the human tongue and lips. This thesis …

Over the past few years, several papers have used Linear Dynamical Systems (LDS) s for
modeling, registration, segmentation, and recognition of visual dynamical processes, such …