Discovering a representation that allows auditory data to be parsimoniously represented is useful for many machine learning and signal processing tasks. Such a representation can ...
In this paper, we propose a novel learning method, called Jensen-Shannon Boosting (JSBoost) and demonstrate its application to object recognition. JSBoost incorporates Jensen-Shan...
A new scheme of data-driven segmentation is proposed, which is based on detection of object boundary, and volumetric pattern reconstruction as implicit function by using the detect...
A successful representation of objects in the literature is as a collection of patches, or parts, with a certain appearance and position. The relative locations of the different p...
A visual word lexicon can be constructed by clustering primitive visual features, and a visual object can be described by a set of visual words. Such a "bag-of-words" re...