Abstract—Becoming proficient in a sport requires significant investment in training. Wearable sensor devices can improve training due to the high level of mobility, ubiquity and...
We introduce two fourth-order regularization methods that remove geometric noise without destroying significant geometric features. These methods leverage ideas from image denoisi...
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...
The 2.1D sketch is a layered representation of occluding and occluded surfaces of the scene. Extracting the 2.1D sketch from a single image is a difficult and important problem ar...
There is a plethora of established and proposed document representation formats but none that can adequately support individual stages within an entire sequence of document image ...