Using a radiosity method to estimate light inter-reflections within large scenes still remains a difficult task. The two main reasons are: (i) the computations entailed by the rad...
Daniel Meneveaux, Kadi Bouatouch, Gilles Subrenat,...
Music classification continues to be an important component of music information retrieval research. An underutilized tool for improving the performance of classifiers is feature ...
Sparse coding of sensory data has recently attracted notable attention in research of learning useful features from the unlabeled data. Empirical studies show that mapping the data...
We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a weakly-supervised manner: the model is learnt from examp...
We propose a highly efficient framework for penalized likelihood kernel methods applied to multiclass models with a large, structured set of classes. As opposed to many previous a...