Please use this identifier to cite or link to this item: https://doi.org/10.1109/ICCV.2013.42
Title: Low-rank sparse coding for image classification
Authors: Zhang, T.
Ghanem, B.
Liu, S. 
Xu, C.
Ahuja, N.
Keywords: bow
image classification
low-rank
Issue Date: 2013
Citation: Zhang, T., Ghanem, B., Liu, S., Xu, C., Ahuja, N. (2013). Low-rank sparse coding for image classification. Proceedings of the IEEE International Conference on Computer Vision : 281-288. ScholarBank@NUS Repository. https://doi.org/10.1109/ICCV.2013.42
Abstract: In this paper, we propose a low-rank sparse coding (LRSC) method that exploits local structure information among features in an image for the purpose of image-level classification. LRSC represents densely sampled SIFT descriptors, in a spatial neighborhood, collectively as low-rank, sparse linear combinations of code words. As such, it casts the feature coding problem as a low-rank matrix learning problem, which is different from previous methods that encode features independently. This LRSC has a number of attractive properties. (1) It encourages sparsity in feature codes, locality in codebook construction, and low-rankness for spatial consistency. (2) LRSC encodes local features jointly by considering their low-rank structure information, and is computationally attractive. We evaluate the LRSC by comparing its performance on a set of challenging benchmarks with that of 7 popular coding and other state-of-the-art methods. Our experiments show that by representing local features jointly, LRSC not only outperforms the state-of-the-art in classification accuracy but also improves the time complexity of methods that use a similar sparse linear representation model for feature coding. © 2013 IEEE.
Source Title: Proceedings of the IEEE International Conference on Computer Vision
URI: http://scholarbank.nus.edu.sg/handle/10635/78216
ISBN: 9781479928392
DOI: 10.1109/ICCV.2013.42
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.