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