Visual categorization with bags of keypoints

Visual categorization with bags of keypoints (2004)

Cached

Download Links

Other Repositories/Bibliography

CiteULike

by Gabriella Csurka , Christopher R. Dance , Lixin Fan , Jutta Willamowski , Cédric Bray

Venue:	In Workshop on Statistical Learning in Computer Vision, ECCV
Citations:	357 - 7 self

Versions

Version History

Metadata Version 1

Datum	Value	Source
TITLE	Visual categorization with bags of keypoints	INFERENCE
AUTHOR NAME	Gabriella Csurka	SVM HeaderParse 0.2
AUTHOR AFFIL	Xerox Research Centre Europe; 6, chemin de Maupertuis	SVM HeaderParse 0.2
AUTHOR ADDR	38240 Meylan, France	SVM HeaderParse 0.2
AUTHOR NAME	Christopher R. Dance	SVM HeaderParse 0.2
AUTHOR AFFIL	Xerox Research Centre Europe; 6, chemin de Maupertuis	SVM HeaderParse 0.2
AUTHOR ADDR	38240 Meylan, France	SVM HeaderParse 0.2
AUTHOR NAME	Lixin Fan	SVM HeaderParse 0.2
AUTHOR AFFIL	Xerox Research Centre Europe; 6, chemin de Maupertuis	SVM HeaderParse 0.2
AUTHOR ADDR	38240 Meylan, France	SVM HeaderParse 0.2
AUTHOR NAME	Jutta Willamowski	SVM HeaderParse 0.2
AUTHOR AFFIL	Xerox Research Centre Europe; 6, chemin de Maupertuis	SVM HeaderParse 0.2
AUTHOR ADDR	38240 Meylan, France	SVM HeaderParse 0.2
AUTHOR NAME	Cédric Bray	SVM HeaderParse 0.2
AUTHOR AFFIL	Xerox Research Centre Europe; 6, chemin de Maupertuis	SVM HeaderParse 0.2
AUTHOR ADDR	38240 Meylan, France	SVM HeaderParse 0.2
ABSTRACT	Abstract. We present a novel method for generic visual categorization: the problem of identifying the object content of natural images while generalizing across variations inherent to the object class. This bag of keypoints method is based on vector quantization of affine invariant descriptors of image patches. We propose and compare two alternative implementations using different classifiers: Naïve Bayes and SVM. The main advantages of the method are that it is simple, computationally efficient and intrinsically invariant. We present results for simultaneously classifying seven semantic visual categories. These results clearly demonstrate that the method is robust to background clutter and produces good categorization accuracy even without exploiting geometric information. 1.	SVM HeaderParse 0.2
YEAR	2004	INFERENCE
VENUE	In Workshop on Statistical Learning in Computer Vision, ECCV	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	1--22	INFERENCE
CITATIONS	27 found	ParsCit 1.0