Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
This paper addresses one of the fundamental problems encountered in performance prediction for object recognition. In particular we address the problems related to estimation of s...
Deformable 3–D models can be represented either as explicit or implicit surfaces. Explicit surfaces, such as triangulations or wire-frame models, are widely accepted in the Comp...
A dynamic texture is a spatio-temporal generative model for video, which represents video sequences as observations from a linear dynamical system. This work introduces the mixtur...
The purpose of this work is to automate the analysis of ad hoc routing protocols in the presence of attackers. To this end, a formal model of protocol behavior is developed in whi...