Paper Info
Title
Supervised Kernel Descriptors for Visual Recognition
Abstract
In visual recognition tasks, the design of low level image feature representation is fundamental. The advent of local patch features from pixel attributes such as SIFT and LBP, has precipitated dramatic progresses. Recently, a kernel view of these features, called kernel descriptors (KDES), generalizes the feature design in an unsupervised fashion and yields impressive results. In this paper, we present a supervised framework to embed the image level label information into the design of patch level kernel descriptors, which we call supervised kernel descriptors (SKDES). Specifically, we adopt the broadly applied bag-of-words (BOW) image classification pipeline and a large margin criterion to learn the low-level patch representation, which makes the patch features much more compact and achieve better discriminative ability than KDES. With this method, we achieve competitive results over several public datasets comparing with state-of-the-art methods.
Year
DOI
Venue
2013
10.1109/CVPR.2013.368
CVPR
Keywords
Field
DocType
image classification pipeline,kernel view,patch level kernel descriptors,visual recognition,low-level patch representation,supervised kernel descriptors,local patch feature,low level image feature,kernel descriptors,feature design,image level label information,vectors,learning artificial intelligence,encoding,image recognition,kernel,image classification,bag of words,dictionaries,accuracy
Kernel (linear algebra),Computer vision,Scale-invariant feature transform,Pattern recognition,Computer science,Image representation,Visual recognition,Pixel,Artificial intelligence,Contextual image classification,Discriminative model,Feature design
Conference
Volume
Issue
ISSN
2013
1
1063-6919
Citations 
PageRank 
References 
19
0.54
35
Authors
6
Name
Order
Citations
PageRank
Peng Wang125312.25
Jingdong Wang24198156.76
Gang Zeng394970.21
Weiwei Xu487550.19
Hongbin Zha52206183.36
Shipeng Li63902252.94