This work characterizes the generalization ability of algorithms whose predictions are linear in the input vector. To this end, we provide sharp bounds for Rademacher and Gaussian...
Traditionally, a logic program is built up to reason about atomic first-order formulas. The key idea of parametrized logic programming is that, instead of atomic first-order form...
The solutions to many vision problems involve integrating measurements from multiple sources. Most existing methods rely on a hidden assumption, i.e., these measurements are consi...
This paper proposes an image segmentation model based on the active contour model, the Mumford-Shah functional and the image decomposition process. Generally speaking, the active ...
Distance metric learning and nonlinear dimensionality reduction are two interesting and active topics in recent years. However, the connection between them is not thoroughly studi...