We introduce new techniques for extracting, analyzing, and visualizing textual contents from instructional videos of low production quality. Using Automatic Speech Recognition, ap...
— Since the different bits of the compressed video sequence produced by the BBC’s wavelet-based video codec exhibit different error sensitivity, efficient Unequal Error Protec...
In this paper we describe a method that estimates the motion of a calibrated camera (settled on an experimental vehicle) and the tridimensional geometry of the environment. The on...
E. Mouragnon, Fabien Dekeyser, Patrick Sayd, Maxim...
Abstract This paper presents an approach to designing and implementing extensible computational models for perceiving systems based on a knowledge-driven joint inference approach. ...
Most work in action recognition deals with sequences acquired by stationary cameras with fixed viewpoints. Due to the camera motion, the trajectories of the body parts contain no...