DocumentCode :
2915358
Title :
Multi-layer group sparse coding — For concurrent image classification and annotation
Author :
Gao, Shenghua ; Chia, Liang-Tien ; Tsang, Ivor Wai-Hung
Author_Institution :
Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
fYear :
2011
fDate :
20-25 June 2011
Firstpage :
2809
Lastpage :
2816
Abstract :
We present a multi-layer group sparse coding framework for concurrent image classification and annotation. By leveraging the dependency between image class label and tags, we introduce a multi-layer group sparse structure of the reconstruction coefficients. Such structure fully encodes the mutual dependency between the class label, which describes the image content as a whole, and tags, which describe the components of the image content. Then we propose a multi-layer group based tag propagation method, which combines the class label and subgroups of instances with similar tag distribution to annotate test images. Moreover, we extend our multi-layer group sparse coding in the Reproducing Kernel Hilbert Space (RKHS) which captures the nonlinearity of features, and further improves performances of image classification and annotation. Experimental results on the LabelMe, UIUC-Sport and NUS-WIDE-Object databases show that our method outperforms the baseline methods, and achieves excellent performances in both image classification and annotation tasks.
Keywords :
Hilbert spaces; computer vision; image classification; image coding; LabelMe database; NUS-WIDE-object database; UIUC-sport database; concurrent image annotation; concurrent image classification; image class label; image class tags; multilayer group based tag propagation method; multilayer group sparse coding framework; reconstruction coefficient multilayer group sparse structure; reproducing kernel Hilbert space; Encoding; Equations; Image coding; Image reconstruction; Kernel; Rocks; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on
Conference_Location :
Providence, RI
ISSN :
1063-6919
Print_ISBN :
978-1-4577-0394-2
Type :
conf
DOI :
10.1109/CVPR.2011.5995454
Filename :
5995454
Link To Document :
بازگشت