The Community for Technology Leaders
2014 IEEE Winter Conference on Applications of Computer Vision (WACV) (2014)
Steamboat Springs, CO, USA
March 24, 2014 to March 26, 2014
ISBN: 978-1-4799-4985-4
pp: 235-240
Somayah Albaradei , Department of Computer Science, University of Manitoba, Canada
Yang Wang , Department of Computer Science, University of Manitoba, Canada
Liangliang Cao , IBM T. J. Watson Research Center, USA
Li-Jia Li , Yahoo Research, USA
ABSTRACT
We propose a new approach for constructing mid-level visual features for image classification. We represent an image using the outputs of a collection of binary classifiers. These binary classifiers are trained to differentiate pairs of object classes in an object hierarchy. Our feature representation implicitly captures the hierarchical structure in object classes. We show that our proposed approach outperforms other baseline methods in image classification.
INDEX TERMS
Feature extraction, Semantics, Animals, Visualization, Footwear, Image representation, Image color analysis
CITATION

S. Albaradei, Yang Wang, L. Cao and L. Li, "Learning mid-level features from object hierarchy for image classification," 2014 IEEE Winter Conference on Applications of Computer Vision (WACV), Steamboat Springs, CO, USA, 2014, pp. 235-240.
doi:10.1109/WACV.2014.6836095
95 ms
(Ver 3.3 (11022016))