Kernel functions can be viewed as a non-linear transformation that increases the separability of the input data by mapping them to a new high dimensional space. The incorporation ...
Human recognition from video requires solving the two tasks, recognition and tracking, simultaneously. This leads to a parameterized time series state space model, representing bo...
— This paper presents a method for vision based estimation of the pose of human hands in interaction with objects. Despite the fact that most robotics applications of human hand ...
We propose extending the concept of spatial constancy to haptic perception. In vision, spatial constancy refers to the conversion of retinotopic signals into spatiotopic represent...
We present an efficient algorithm for continuous image
recognition and feature descriptor tracking in video which
operates by reducing the search space of possible interest
poin...
Duy-Nguyen Ta (Georgia Institute of Technology), W...