We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and po...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...
Based on the overall aims of the AdeLE (Adaptive e-Learning with Eye-Tracking) project, and in particular motivated by the decision of using a strictly separated system’s archit...
In this paper we describe a method to learn parameters
which govern pedestrian motion by observing video
data. Our learning framework is based on variational
mode learning and a...
Hidden Markov models have become the preferred technique for visual recognition of human gestures. However, the recognition rate depends on the set of visual features used, and al...
Background: Many commonly used genome browsers display sequence annotations and related attributes as horizontal data tracks that can be toggled on and off according to user prefe...
Mary E. Dolan, Constance C. Holden, M. Kate Beard,...