Show simple item record

dc.contributor.authorZhang, X.
dc.contributor.authorPham, DucSon
dc.contributor.authorPhung, D.
dc.contributor.authorLiu, Wan-Quan
dc.contributor.authorSaha, B.
dc.contributor.authorVenkatesh, S.
dc.date.accessioned2017-01-30T15:10:24Z
dc.date.available2017-01-30T15:10:24Z
dc.date.created2015-10-29T04:09:29Z
dc.date.issued2015
dc.identifier.citationZhang, X. and Pham, D. and Phung, D. and Liu, W. and Saha, B. and Venkatesh, S. 2015. Visual object clustering via mixed-norm regularization, in Proceedings of the 2015 IEEE Winter Conference on Applications of Computer Vision, Jan 5-9 2015, pp. 1030-1037. Waikoloa, Hl: Institute of Electrical and Electronics Engineers Inc.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/43834
dc.identifier.doi10.1109/WACV.2015.142
dc.description.abstract

Many vision problems deal with high-dimensional data, such as motion segmentation and face clustering. However, these high-dimensional data usually lie in a low-dimensional structure. Sparse representation is a powerful principle for solving a number of clustering problems with high-dimensional data. This principle is motivated from an ideal modeling of data points according to linear algebra theory. However, real data in computer vision are unlikely to follow the ideal model perfectly. In this paper, we exploit the mixed norm regularization for sparse subspace clustering. This regularization term is a convex combination of the l1norm, which promotes sparsity at the individual level and the block norm l2/1 which promotes group sparsity. Combining these powerful regularization terms will provide a more accurate modeling, subsequently leading to a better solution for the affinity matrix used in sparse subspace clustering. This could help us achieve better performance on motion segmentation and face clustering problems. This formulation also caters for different types of data corruptions. We derive a provably convergent algorithm based on the alternating direction method of multipliers (ADMM) framework, which is computationally efficient, to solve the formulation. We demonstrate that this formulation outperforms other state-of-arts on both motion segmentation and face clustering.

dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.titleVisual object clustering via mixed-norm regularization
dc.typeConference Paper
dcterms.source.startPage1030
dcterms.source.endPage1037
dcterms.source.titleProceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
dcterms.source.seriesProceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
dcterms.source.isbn9781479966820
curtin.departmentDepartment of Computing
curtin.accessStatusFulltext not available


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record