logo Idiap Research Institute        
 [BibTeX] [Marc21]
Learning to Retrieve Images from Text Queries with a Discriminative Model
Type of publication: Idiap-RR
Citation: grangier:2006:idiap-06-32
Number: Idiap-RR-32-2006
Year: 2006
Institution: IDIAP
Abstract: This work presents a discriminative model for the retrieval of pictures from text queries. The core idea of this approach is to minimize a loss directly related to the retrieval performance of the model. For that purpose, we rely on a ranking loss which has recently been successfully applied to text retrieval problems. The experiments performed over the Corel dataset show that our approach compares favorably with generative models that constitute the state-of-the-art (e.g. our model reaches 21.6\% mean average precision with Blob and SIFT features, compared to 16.7\% for PLSA, the best alternative).
Userfields: ipdmembership={learning},
Projects Idiap
Authors Grangier, David
Monay, Florent
Bengio, Samy
Crossref by grangier:2006:amr
Added by: [UNK]
Total mark: 0
  • grangier_rr06-32.pdf
  • grangier_rr06-32.ps.gz