Acquiring dynamic 3D fluid surfaces is a challenging problem in computer vision. Single or stereo camera based solutions are sensitive to refraction distortions, fast fluid moti...
We describe an architecture for representing and managing context shifts that supports dynamic data interpretation. This architecture utilizes two layers of learning and three lay...
Nikita A. Sakhanenko, George F. Luger, Carl R. Ste...
OpenCV is a C/C++ computer vision library originally developed by Intel. It is free for commercial and research use under a BSD license. The library is cross-platform.
It is highl...
We introduce Gaussian process dynamical models (GPDMs) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensional motio...
This paper develops the concept of usefulness in the context of supervised learning. We argue that usefulness can be used to improve the performance of classification rules (as me...
Gholamreza Nakhaeizadeh, Charles Taylor, Carsten L...