LEARNING THE SEMANTICS OF MULTIMEDIA CONTENT WITH APPLICATION TO WEB IMAGE RETRIEVAL AND CLASSIFICATION
Alexei Vinokourov, David Roi Hardoon, John S. Shawe-Taylor · ePrints Soton (University of Southampton) · 2003
We use kernel Canonical Correlation Analysis to learn a se-mantic representation of Web images and their associated text. This representation is used in two applications. In first application we consider classification of images into one of three categories. We use SVM in the semantic space and compare against the SVM on raw data and against previ-ously published results using ICA. In the second applica-tion we retrieve images based only on their content from a text query. The semantic space provides a common rep-resentation and enables a comparison between the text and image. We compare against a standard cross-representation retrieval technique known as the Generalised Vector Space Model. 1. INTRODUCTION AND PREVIOUS