The present study examined the human ability to learn a new sensory modality, specifically "whisking". An experimental apparatus containing artificial whiskers, force sen...
Categories in multi-class data are often part of an underlying semantic taxonomy. Recent work in object classification has found interesting ways to use this taxonomy structure t...
Statistical methods, such as independent component analysis, have been successful in learning local low-level features from natural image data. Here we extend these methods for le...
This paper presents a new face identification system based on Graph Matching Technique on SIFT features extracted from face images. Although SIFT features have been successfully us...
We propose a method for simultaneous detection, localization and segmentation of objects of a known category. We show that this is possible by using segments as features. To this ...