We propose a novel framework to build descriptors of local intensity that are invariant to general deformations. In this framework, an image is embedded as a 2D surface in 3D spac...
Local image features or interest points provide compact ract representations of patterns in an image. In this paper, we propose to extend the notion of spatial interest points int...
This paper discusses building complex classifiers from a single labeled example and vast number of unlabeled observation sets, each derived from observation of a single process or...
Abstract. The use of sparse invariant features to recognise classes of actions or objects has become common in the literature. However, features are often "engineered" to...
The joint tasks of object recognition and object segmentation from a single image are complex in their requirement of not only correct classification, but also deciding exactly whi...