TELECOM ParisTech at ImageClef 2009: Large Scale Visual Concept Detection and Annotation Task
Marin Ferecatu, Hichem Sahbi · CLEF (Working Notes) · 2009
In this paper we describe the participation of TELECOM ParisTech in the Large Scale Visual Concept Detection and Annotation Task at the ImageClef 2009 challenge. This year, the focus was in the extension of (i) the amount of data available for tr aining and testing, and (ii) the number of concepts to be annotated. We use Canonical Correlation Analysis in order to infer a latent space where text and visual description are highly correlated. Starting from a visual description of a test image, we first map it into the latent spa ce, then we predict the underlying text features (and also annotations) which best fit the visua l ones in the latent space. Our method is very fast while achieving good results.