In this paper a method for fitting open surfaces to an unorganized set of data points is presented using a level set representation of the surface. This is done by tracking a curv...
We propose a unified framework based on a general definition of geometric transform (GeT) for modeling appearance. GeT represents the appearance by applying designed functionals o...
Abstract. We propose a novel method for action detection based on a new action descriptor called a shape flow that represents both the shape and movement of an object in a holistic...
This paper proposes a framework of scalable motion estimation and coding with the structure of multi-layers for 3D wavelet video coding. The motion representation consists of mult...
It has been pointed out repeatedly that spatial operations must be extended to include support for 3D and moving objects. The attempt to code by hand each spatial operation for ea...
Farid Karimipour, Andrew U. Frank, Mahmoud Reza De...