Abstract. In this paper, we present novel image-derived, invariant features that accurately capture both the geometric and color properties of an imaged object. These features can ...
Discriminative learning is challenging when examples are sets of features, and the sets vary in cardinality and lack any sort of meaningful ordering. Kernel-based classification m...
Action recognition is one of the most active research fields in computer vision. In this paper, we propose a novel method for classifying human actions in a series of image seque...