Timezone: »

Portmanteau Vocabularies for Multi-Cue Image Representation
Fahad S Khan · Joost van de Weijer · Andrew D Bagdanov · Maria Vanrell

Mon Dec 12 10:00 AM -- 02:59 PM (PST) @

We describe a novel technique for feature combination in the bag-of-words model of image classification. Our approach builds discriminative compound words from primitive cues learned independently from training images. Our main observation is that modeling joint-cue distributions independently is more statistically robust for typical classification problems than attempting to empirically estimate the dependent, joint-cue distribution directly. We use Information theoretic vocabulary compression to find discriminative combinations of cues and the resulting vocabulary of portmanteau words is compact, has the cue binding property, and supports individual weighting of cues in the final image representation. State-of-the-art results on both the Oxford Flower-102 and Caltech-UCSD Bird-200 datasets demonstrate the effectiveness of our technique compared to other, significantly more complex approaches to multi-cue image representation

Author Information

Fahad S Khan (Computer Vision Center)
Joost van de Weijer (Computer Vision Center Barcelona)
Andrew D Bagdanov (University of Florence.)
Maria Vanrell (Computer Vision Center)

More from the Same Authors