CONF grangier:2006:amr/IDIAP Learning to Retrieve Images from Text Queries with a Discriminative Model Grangier, David Monay, Florent Bengio, Samy EXTERNAL https://publications.idiap.ch/attachments/reports/2006/grangier_amr06.pdf PUBLIC https://publications.idiap.ch/index.php/publications/showcite/grangier:2006:idiap-06-32 Related documents International Workshop on Adaptive Multimedia Retrieval (AMR) 2006 42-56 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). REPORT grangier:2006:idiap-06-32/IDIAP Learning to Retrieve Images from Text Queries with a Discriminative Model Grangier, David Monay, Florent Bengio, Samy EXTERNAL https://publications.idiap.ch/attachments/reports/2006/grangier_rr06-32.pdf PUBLIC Idiap-RR-32-2006 2006 IDIAP 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).