Abstract. We address the problem of learning good features for understanding video data. We introduce a model that learns latent representations of image sequences from pairs of su...
For effective retrieval of visual information, statistical learning plays a pivotal role. Statistical learning in such a context faces at least two major mathematical challenges: ...
Exponential models of distributions are widely used in machine learning for classification and modelling. It is well known that they can be interpreted as maximum entropy models u...
We consider the application of machine learning techniques for sequence modeling to Information Retrieval (IR) and surface Information Extraction (IE) tasks. We introduce a generi...
Massih-Reza Amini, Hugo Zaragoza, Patrick Gallinar...
We present a strategy for analyzing large, social small-world graphs, such as those formed by human networks. Our approach brings together ideas from a number of different resear...