000146415 001__ 146415
000146415 005__ 20190316234731.0
000146415 037__ $$aREP_WORK
000146415 245__ $$aLearning to Retrieve Images from Text Queries with a Discriminative Model
000146415 269__ $$a2006
000146415 260__ $$bIDIAP$$c2006
000146415 336__ $$aReports
000146415 520__ $$aThis work presents a discriminative model for the retrieval of pictures from text queries. The core idea of this approach is to minimize a loss directly related to the retrieval performance of the model. For that purpose, we rely on a ranking loss which has recently been successfully applied to text retrieval problems. The experiments performed over the Corel dataset show that our approach compares favorably with generative models that constitute the state-of-the-art (e.g. our model reaches 21.6\% mean average precision with Blob and SIFT features, compared to 16.7\% for PLSA, the best alternative).
000146415 700__ $$0241067$$aGrangier, David$$g166608
000146415 700__ $$aMonay, Florent
000146415 700__ $$0243961$$aBengio, Samy$$g140142
000146415 8564_ $$uhttp://publications.idiap.ch/downloads/reports/2006/grangier_rr06-32.pdf$$zURL
000146415 8564_ $$s261597$$uhttps://infoscience.epfl.ch/record/146415/files/grangier_rr06-32.pdf$$zn/a
000146415 909C0 $$0252189$$pLIDIAP$$xU10381
000146415 909CO $$ooai:infoscience.tind.io:146415$$pSTI$$preport$$qGLOBAL_SET
000146415 937__ $$aLIDIAP-REPORT-2006-032
000146415 970__ $$agrangier:2006:idiap-06-32/LIDIAP
000146415 973__ $$aEPFL$$sPUBLISHED
000146415 980__ $$aREPORT