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 ...
In this paper, we present an approach we refer to as "least squares congealing" which provides a solution to the problem of aligning an ensemble of images in an unsuperv...
Mark Cox, Sridha Sridharan, Simon Lucey, Jeffrey F...
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...
In the framework of a face verification system using local features and a Gaussian Mixture Model based classifier, we address the problem of non-frontal face verification (when on...
Quantization index modulation (QIM) techniques have been gaining popularity in the data hiding community because of their robustness and information-theoretic optimality against a...