In this paper we propose an approach capable of simultaneous recognition and localization of multiple object classes using a generative model. A novel hierarchical representation ...
In patch-based object recognition, there are two important issues on the codebook generation: (1) resolution: a coarse codebook lacks sufficient discriminative power, and an over-...
We present a framework for learning features for visual discrimination. The learning system is exposed to a sequence of training images. Whenever it fails to recognize a visual co...
This paper presents a morphological scale-space approach to the problem of feature extraction. The method relies on two steps: a hierarchical simplification step based on pyramids...
We introduce the use of weighted medial graph structures to represent sounds and musical events. Such structures permit the building of hierarchical neighborhood relationships (sy...
Alex McLean, Frederic F. Leymarie, Geraint A. Wigg...