Please use this identifier to cite or link to this item: https://doi.org/10.1145/2379790.2379792
Title: Label-to-region with continuity-biased bi-layer sparsity Priors
Authors: Liu, X. 
Yan, S. 
Cheng, B.
Tang, J.
Chua, T.-S. 
Jin, H.
Keywords: Bag-of-hierarchical-patch
Image annotation
Label-to-Region
Sparse representation
Issue Date: 2012
Source: Liu, X., Yan, S., Cheng, B., Tang, J., Chua, T.-S., Jin, H. (2012). Label-to-region with continuity-biased bi-layer sparsity Priors. ACM Transactions on Multimedia Computing, Communications and Applications 8 (4) : -. ScholarBank@NUS Repository. https://doi.org/10.1145/2379790.2379792
Abstract: In this work, we investigate how to reassign the fully annotated labels at image level to those contextually derived semantic regions, namely Label-to-Region (L2R), in a collective manner. Given a set of input images with label annotations, the basic idea of our approach to L2R is to first discover the patch correspondence across images, and then propagate the common labels shared in image pairs to these correlated patches. Specially, our approach consists of following aspects. First, each of the input images is encoded as a Bag-of-Hierarchical-Patch (BOP) for capturing the rich cues at variant scales, and the individual patches are expressed by patch-level feature descriptors. Second, we present a sparse representation formulation for discovering how well an image or a semantic region can be robustly reconstructed by all the other image patches from the input image set. The underlying philosophy of our formulation is that an image region can be sparsely reconstructed with the image patches belonging to the other images with common labels, while the robustness in label propagation across images requires that these selected patches come from very few images. This preference of being sparse at both patch and image level is named bi-layer sparsity prior. Meanwhile, we enforce the preference of choosing larger-size patches in reconstruction, referred to as continuitybiased prior in this work, which may further enhance the reliability of L2R assignment. Finally, we harness the reconstruction coefficients to propagate the image labels to the matched patches, and fuse the propagation results over all patches to finalize the L2R task. As a by-product, the proposed continuity-biased bi-layer sparse representation formulation can be naturally applied to perform image annotation on new testing images. Extensive experiments on three public image datasets clearly demonstrate the effectiveness of our proposed framework in both L2R assignment and image annotation. © 2012 ACM.
Source Title: ACM Transactions on Multimedia Computing, Communications and Applications
URI: http://scholarbank.nus.edu.sg/handle/10635/56448
ISSN: 15516857
DOI: 10.1145/2379790.2379792
Appears in Collections:Staff Publications

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

SCOPUSTM   
Citations

8
checked on Dec 5, 2017

WEB OF SCIENCETM
Citations

4
checked on Nov 14, 2017

Page view(s)

76
checked on Dec 9, 2017

Google ScholarTM

Check

Altmetric


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