Abstract. Most current approaches to recognition aim to be scaleinvariant. However, the cues available for recognizing a 300 pixel tall object are qualitatively different from tho...
Previous work demonstrated that web counts can be used to approximate bigram frequencies, and thus should be useful for a wide variety of NLP tasks. So far, only two generation ta...
The intuition behind ensembles is that different prediciton models compensate each other’s errors if one combines them in an appropriate way. In case of large ensembles a lot of...
Krisztian Buza, Alexandros Nanopoulos, Lars Schmid...