In various applications, the effect of errors in gradient-based iterations is of particular importance when seeking saddle points of the Lagrangian function associated with constra...
Efficient and accurate fitting of Active Appearance
Models (AAM) is a key requirement for many applications.
The most efficient fitting algorithm today is Inverse Compositional
...
Brian Amberg (University of Basel), Andrew Blake (...
In this paper, we propose a robust model selection criterion for mixtures of subspaces called minimum effective dimension (MED). Previous information-theoretic model selection cri...
We present a method for training a similarity metric from data. The method can be used for recognition or verification applications where the number of categories is very large an...
Many computer vision applications, such as scene analysis and medical image interpretation, are ill-suited for traditional classification where each image can only be associated w...