We present spatio-temporal feature descriptors that can be inferred from video and used as building blocks in action recognition systems. They capture the evolution of ``elementar...
We propose a new pen-based text input method, which is an integration of software keyboards, handwriting recognition, and marking menus. With our method, a user selects a word fro...
A scheme for pose-independent face recognition is presented. An "unwrapped" texture map is constructed from a video sequence using a texture-from-motion approach, which ...
Live closed-captions for deaf and hard of hearing audiences are currently produced by stenographers, or by voice writers using speech recognition. Both techniques can produce capt...
Patrick Cardinal, Gilles Boulianne, Michel Comeau,...
We present a methodology to analyze Multiple Classifiers Systems (MCS) performance, using the disagreement concept. The goal is to define an alternative approach to the conventiona...