The recent non-uniform subdivision approach extends traditional uniform subdivision schemes with variable rules, offering additional shape parameters (such as knot spacings) for f...
We present a Dynamic Data Driven Application System (DDDAS) to track 2D shapes across large pose variations by learning non-linear shape manifold as overlapping, piecewise linear s...
We consider the important challenge of recognizing a variety of deformable object classes in images. Of fundamental importance and particular difficulty in this setting is the pro...
We propose a hybrid body representation that represents each typical pose by both template-like view information and part-based structural information. Specifically, each body par...
We describe some techniques that can be used to represent and detect deformable shapes in images. The main difficulty with deformable template models is the very large or infinite...