Choosing good features to represent objects can be crucial to the success of supervised machine learning algorithms. Good high-level features are those that concentrate informatio...
The nature of the internet as a non-peer-reviewed (and more generally largely unregulated) publication medium has allowed wide-spread promotion of inaccurate and unproven medical ...
We propose a method for reconstruction of human brain states directly from functional neuroimaging data. The method extends the traditional multivariate regression analysis of dis...
Sennay Ghebreab, Arnold W. M. Smeulders, Pieter W....
— In this paper, we present a new approach for automatic car detection from aerial images. The system exploits a robust machine learning method known as boosting for efficient c...
Thuy Thi Nguyen, Helmut Grabner, Horst Bischof, B....
We propose an unsupervised approach to learn associations between continuous-valued attributes from different modalities. These associations are used to construct a multi-modal t...