Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/81696
Title: Concurrent Single-Label Image Classification and Annotation via Efficient Multi-Layer Group Sparse Coding
Authors: Gao, Shenghua
Chia, Liang-Tien
Tsang, Ivor Wai-Hung
Ren, Zhixiang
Keywords: Image annotation
Sparse coding
Image classification
Kernel trick
Issue Date: 2014
Source: Gao, S., Chia, L.-T., Tsang, I. W.-H., & Ren, Z. (2014). Concurrent Single-Label Image Classification and Annotation via Efficient Multi-Layer Group Sparse Coding. IEEE Transactions on Multimedia, 16(3), 762-771.
Series/Report no.: IEEE Transactions on Multimedia
Abstract: We present a multi-layer group sparse coding framework for concurrent single-label 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 image content as a whole, and tags, which describe the components of the image content. Therefore 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. To make our model more suitable for nonlinear separable features, we also extend our multi-layer group sparse coding in the Reproducing Kernel Hilbert Space (RKHS), which further improves performances of image classification and annotation. Moreover, we also integrate our multi-layer group sparse coding with kNN strategy, which greatly improves the computational efficiency. Experimental results on the LabelMe, UIUC-Sports and NUS-WIDE-Object databases show that our method outperforms the baseline methods, and achieves excellent performances in both image classification and annotation tasks.
URI: https://hdl.handle.net/10356/81696
http://hdl.handle.net/10220/39673
ISSN: 1520-9210
DOI: 10.1109/TMM.2014.2299516
Rights: © 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: [http://dx.doi.org/10.1109/TMM.2014.2299516].
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Google ScholarTM

Check

Altmetric

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.