We describe an approach to object and scene retrieval which searches for and localizes all the occurrences of a user outlined object in a video. The object is represented by a set...
We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns...
Florent Monay, Pedro Quelhas, Daniel Gatica-Perez,...
We address the problem of computing joint sparse representation of visual signal across multiple kernel-based representations. Such a problem arises naturally in supervised visual...
It is well known that many Web pages are difficult for visually disabled people to use. Without access to a rich, visual display, the intended structure and organisation of the pa...
Caroline Jay, Robert Stevens, Mashhuda Glencross, ...
Visualizations of space, time, and agents (or objects) are ubiquitous in science, business, and everyday life, from weather maps to scheduling meetings. Effective communications, i...