We study in this paper the problem of bridging the semantic gap between low-level image features and high-level semantic concepts, which is the key hindrance in content-based imag...
Much of the world’s data is in the form of time series, and many other types of data, such as video, image, and handwriting, can easily be transformed into time series. This fact...
Distance functions are an important component in many learning applications. However, the correct function is context dependent, therefore it is advantageous to learn a distance f...
In this paper, we propose a novel metric learning method based on regularized moving least squares. Unlike most previous metric learning methods which learn a global Mahalanobis d...
We pose the recognition problem as data association. In this setting, a novel object is explained solely in terms of a small set of exemplar objects to which it is visually simila...