Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...
In previous work [7] a computational framework was demonstrated that employs evolutionary algorithms to automatically model a given system. This is accomplished by alternating the...
We propose a new image registration criterion that uses segmented versions of the images to exploit both the geometric and photometric characteristics of the distinct regions they...
Monaural speech segregation in reverberant environments is a very difficult problem. We develop a supervised learning approach by proposing an objective function that directly rel...
We present a new Web services-based framework for building componentized digital libraries (DLs). We particularly demonstrate how traditional RDBMS technology can be easily deploy...
Rodrygo L. T. Santos, Pablo A. Roberto, Marcos And...