Expanded bag of words representation for object classification

Authors:
Tinglin Liu;Jing Liu;Qinshan Liu;Hanqing Lu
Affiliations:
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China;National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Science, Beijing, China
Venue:
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Year:
2009

Citing 5
Cited 0

Concept based query expansion

SIGIR '93 Proceedings of the 16th annual international ACM SIGIR conference on Research and development in information retrieval
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Shape Matching and Object Recognition Using Low Distortion Correspondences

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study

International Journal of Computer Vision
Sampling strategies for bag-of-features image classification

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV

Quantified Score

Hi-index	0.01

Visualization

Abstract

Currently, the bag of visual words (BOW) representation has received wide applications in object categorization. However, the BOW representation ignores the dependency relationship among visual words, which could provide informative knowledge to understand an image. In this paper, we first design a simple method to discover this dependency through computing the spatial correlation between visual words in overlapped local patches. Obtaining the dependency relationship, we further propose a novel update strategy to modify the BOW representation. The modification is motivated by the idea of Query Expansion applied successfully in text retrieval. We implement our approach on challenging PASCAL 2006 database, and the experimental results show its improved performance against the BOW representation.