In order to evaluate automated image annotation and object recognition algorithms, ground
truth in the form of a set of images correctly annotated with text describing each image is …

We introduce an approach to learn discriminative visual representations while exploiting
external semantic knowledge about object category relationships. Given a hierarchical …

This dissertation investigates the system-centred evaluation of visual information retrieval
from generic photographic collections. The development of visual information retrieval …

Visual object category recognition is one of the most challenging problems in computer
vision. Even assuming that we can obtain a near-perfect instance level representation with …

We consider strategies for reducing ambiguity in multi-modal data, particularly in the domain
of images and text. Large data sets containing images with associated text (and vice versa) …

In the field of computer vision, automated image annotation and object recognition are
currently important research topics. It is hoped that these will lead to improved general …

A review of multimedia annotation techniques, in particular image annotation, is presented.
The annotation requirements for the Benchmarking workpackage of the MUSCLE EU …