in this paper the problem of 3d scene and object classification from depth data is addressed. in contrast to high-dimensional feature-based representation, the depth data is described in a low dimensional space. in order to remedy the curse of dimensionality problem, the depth data is described by a sparse model over a learned dictionary. exploiting the algorithmic information theory, a new def...

This formula can be informally read as follows: the ith messagemi brings us log(1=pi) "bits of information" (whatever this means), and appears with frequency pi, so H is expected amount information provided by one random message (one sample variable). Moreover, we construct an optimal uniquely decodable code that requires about (at most + 1, to exact) bits per on average, it encodes approximate...