TY - GEN
T1 - Beyond bags of features
T2 - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
AU - Lazebnik, Svetlana
AU - Schmid, Cordelia
AU - Ponce, Jean
PY - 2006
Y1 - 2006
N2 - This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting "spatial pyramid" is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralba's "gist" and Lowe's SIFT descriptors.
AB - This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting "spatial pyramid" is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralba's "gist" and Lowe's SIFT descriptors.
UR - http://www.scopus.com/inward/record.url?scp=33845572523&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=33845572523&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2006.68
DO - 10.1109/CVPR.2006.68
M3 - Conference contribution
AN - SCOPUS:33845572523
SN - 0769525970
SN - 9780769525976
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2169
EP - 2178
BT - Proceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Y2 - 17 June 2006 through 22 June 2006
ER -