TY  - CONF
AU  - Fahad Shahbaz Khan
AU  - Joost Van de Weijer
AU  - Andrew Bagdanov
AU  - Maria Vanrell
A2  - NIPS
PY  - 2011//
TI  - Portmanteau Vocabularies for Multi-Cue Image Representation
BT  - 25th Annual Conference on Neural Information Processing Systems
N2  - 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
UR  - http://nips.cc/Conferences/2011/Program/event.php?ID=2765
L1  - http://refbase.cvc.uab.es/files/KWB2011.pdf
N1  - CIC
ID  - Fahad Shahbaz Khan2011
ER  -