The advantage of a kernel method often depends critically on a proper choice of the kernel function. A promising approach is to learn the kernel from data automatically. In this p...
This paper gives an overview of recent approaches towards image representation and image similarity computation for content-based image retrieval and automatic image annotation (ca...
Abstract. The importance of spatial configuration information for object class recognition is widely recognized. Single isolated local appearance codes are often ambiguous. On the...
We introduce an exemplar model that can learn and generate a region of interest around class instances in a training set, given only a set of images containing the visual class. T...
We present a novel approach to weakly supervised semantic class learning from the web, using a single powerful hyponym pattern combined with graph structures, which capture two pr...