This paper presents a new algorithm for the automatic recognition of object classes from images (categorization). Compact and yet discriminative appearance-based object class mode...
In this paper, we present a novel approach to learning semantic localized patterns with binary projections in a supervised manner. The pursuit of these binary projections is refor...
Aggregating statistical representations of classes is an important task for current trends in scaling up learning and recognition, or for addressing them in distributed infrastruc...
Human behavior recognition is one of the most important and challenging objectives performed by intelligent vision systems. Several issues must be faced in this domain ranging fro...
Recently, the bag-of-words approach has been successfully applied to automatic image annotation, object recognition, etc. The method needs to first quantize an image using the vis...