Existing approaches to multi-view learning are particularly effective when the views are either independent (i.e, multi-kernel approaches) or fully dependent (i.e., shared latent ...
Mathieu Salzmann, Carl Henrik Ek, Raquel Urtasun, ...
Given a matrix A, it is often desirable to find a good approximation to A that has low rank. We introduce a simple technique for accelerating the computation of such approximation...
Most state-of-the-art approaches to action recognition rely on global representations either by concatenating local information in a long descriptor vector or by computing a single...
Systemic pathways-oriented approaches to analysis of metabolic networks are effective for small networks but are computationally infeasible for genome scale networks. Current comp...
Nagiza F. Samatova, Al Geist, George Ostrouchov, A...
We consider the problem of transforming a signal to a representation in which the components are statistically independent. When the signal is generated as a linear transformation...