A new approach to the recognition of temporal behaviors and activities is presented. The fundamental idea, inspired by work in speech recognition, is to divide the inference probl...
This work presents a piecewise linear approximation to non-linear Point Distribution Models for modelling the human hand. The work utilises the natural segmentation of shape space...
We address the character identification problem in
movies and television videos: assigning names to faces on
the screen. Most prior work on person recognition in video
assumes s...
Timothee Cour, Benjamin Sapp, Akash Nagle, Ben Tas...
The CTTN-system is a computer program which provides advanced processing or temporal notions. The basic data structures of the CTTN-system are time points, crisp and fuzzy time int...
We present a method to automatically extract spatio-temporal descriptions of moving objects from synchronized and calibrated multi-view sequences. The object is modeled by a time-...