In this demonstration we present SHIATSU, an automatic semantic-based video tagging system which relies on shot boundary detection and hierarchical annotation. More in details, in...
Traditionally, the use of untranscribed speech has been restricted to unsupervised or semi-supervised training of acoustic models. Comparison of recognizers has required labeled d...
The early classifications of the computational complexity of planning under various restrictions in STRIPS (Bylander) and SAS+ (B¨ackstr¨om and Nebel) have influenced followin...
A critical function in both machine vision and biological vision systems is attentional selection of scene regions worthy of further analysis by higher-level processes such as obj...
We propose a method that combines signals from many brain regions observed in functional Magnetic Resonance Imaging (fMRI) to predict the subject’s behavior during a scanning se...