In semi-supervised learning, a number of labeled examples are usually required for training an initial weakly useful predictor which is in turn used for exploiting the unlabeled e...
Graph based semi-supervised learning methods (SSL) implicitly assume that the intrinsic geometry of the data points can be fully specified by an Euclidean distance based local ne...
Abstract. In this paper we present a new approach for establishing correspondences between sparse image features related by an unknown non-rigid mapping and corrupted by clutter an...
Lorenzo Torresani, Vladimir Kolmogorov, Carsten Ro...
This paper presents a new discriminative model for information retrieval (IR), referred to as linear discriminant model (LDM), which provides a flexible framework to incorporate a...
This paper addresses the problem of learning similaritypreserving binary codes for efficient retrieval in large-scale image collections. We propose a simple and efficient altern...