Title
Undoing the codebook bias by linear transformation with sparsity and F-norm constraints for image classification.
Abstract
•We propose a novel linear codebook transformation method to undo the image dataset bias.•We alternatively optimize over the linear transformation matrix and encoding parameters.•We achieve comparable performance with codebook generated by the corresponding image dataset.
Year
DOI
Venue
2014
10.1016/j.patrec.2014.04.002
Pattern Recognition Letters
Keywords
Field
DocType
Codebook bias,Linear transformation,Sparsity,Alternative optimization
Computer vision,Feature vector,Linear independence,U-matrix,Linde–Buzo–Gray algorithm,Bag-of-words model in computer vision,Pattern recognition,Artificial intelligence,Transformation matrix,Mathematics,Codebook,Visual Word
Journal
Volume
ISSN
Citations 
45
0167-8655
1
PageRank 
References 
Authors
0.35
33
7
Name
Order
Citations
PageRank
Chunjie Zhang148239.70
Chao Liang2105977.92
Junbiao Pang319315.81
Yifan Zhang451230.27
Jing Liu5178188.09
Lei Qin651527.67
Qingming Huang73919267.71