Boosting is a popular approach for building accurate classifiers. Despite the initial popular belief, boosting algorithms do exhibit overfitting and are sensitive to label noise. ...
We present novel semi-supervised boosting algorithms that incrementally build linear combinations of weak classifiers through generic functional gradient descent using both labele...
The importance of accurate early diagnostics of dyslexia that severely affects the learning abilities of children cannot be overstated. Neuropathological studies have revealed an ...
Ayman El-Baz, Manuel Casanova, Georgy L. Gimel'far...
Abstract— We present as a contribution to the field of humanmachine interaction a system that analyzes human movements online through multiple observers, based on the concept of...
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...