We describe an improved, anatomically based approach to modeling and animating animals. Underlying muscles, bones, and generalized tissue are modeled as triangle meshes or ellipso...
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...
This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...
The aim of motion detection is to decide whether a given part of an image belongs to a moving object or to the static background. This paper proposes an automatic decision rule for...
In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...