TY  - JOUR
AU  - Noha Elfiky
AU  - Fahad Shahbaz Khan
AU  - Joost Van de Weijer
AU  - Jordi Gonzalez
PY  - 2012//
TI  - Discriminative Compact Pyramids for Object and Scene Recognition
T2  - PR
JO  - Pattern Recognition
SP  - 1627
EP  - 1636
VL  - 45
IS  - 4
N2  - Spatial pyramids have been successfully applied to incorporating spatial information into bag-of-words based image representation. However, a major drawback is that it leads to high dimensional image representations. In this paper, we present a novel framework for obtaining compact pyramid representation. First, we investigate the usage of the divisive information theoretic feature clustering (DITC) algorithm in creating a compact pyramid representation. In many cases this method allows us to reduce the size of a high dimensional pyramid representation up to an order of magnitude with little or no loss in accuracy. Furthermore, comparison to clustering based on agglomerative information bottleneck (AIB) shows that our method obtains superior results at significantly lower computational costs. Moreover, we investigate the optimal combination of multiple features in the context of our compact pyramid representation. Finally, experiments show that the method can obtain state-of-the-art results on several challenging data sets.
SN  - 0031-3203
UR  - http://www.sciencedirect.com/science/article/pii/S0031320311003992
L1  - http://refbase.cvc.uab.es/files/EKW2012.pdf
UR  - http://dx.doi.org/10.1016/j.patcog.2011.09.020
N1  - ISE; CAT;CIC
ID  - Noha Elfiky2012
ER  -