Towards a more balanced model of language acquisition – We present a new method for improving human performance due to the use of high-level features extracted from linguistic resources. We show that our method can outperform other approaches on two tasks, both of which are currently unsolved.

In this paper we present a methodology for the classification of videos in which humans are involved. We build a system to classify videos and make them more informative for video content. We present a video classification system on the basis of a visual similarity measure, a new category of images and content on which we propose to classify images. The classification process is based on a multi-scale classifier which employs a visual similarity measure, a new category of images and content, and a new category of videos which provides a visual similarity measure. Experimental results show that the proposed system is significantly more accurate than the state-of-the-art method in terms of accuracy and speed.

From Word Sense Disambiguation to Semantic Regularities

A Fast Convex Formulation for Unsupervised Model Selection on Graphs

Towards a more balanced model of language acquisition

Rationalization: A Solved Problem with Rational Probabilities?

Learning A New Visual Feature from VideosIn this paper we present a methodology for the classification of videos in which humans are involved. We build a system to classify videos and make them more informative for video content. We present a video classification system on the basis of a visual similarity measure, a new category of images and content on which we propose to classify images. The classification process is based on a multi-scale classifier which employs a visual similarity measure, a new category of images and content, and a new category of videos which provides a visual similarity measure. Experimental results show that the proposed system is significantly more accurate than the state-of-the-art method in terms of accuracy and speed.