Low Rank Representation on SPD matrices with Log-Euclidean metric
作者：
Highlights：
• Proposing a novel LRR model on SPD matrices space with Log-Euclidean metric, namely LogELRR. This is different from the model proposed in [15] where the LRR was implemented in the tangent space of the manifold thus it is a first order approximation to the manifold.
• Providing kernelise extensions of LogELRR method.
• Deriving an optimization problem which has a closed-form solution makes our proposed algorithms faster.
摘要
•Proposing a novel LRR model on SPD matrices space with Log-Euclidean metric, namely LogELRR. This is different from the model proposed in [15] where the LRR was implemented in the tangent space of the manifold thus it is a first order approximation to the manifold.•Providing kernelise extensions of LogELRR method.•Deriving an optimization problem which has a closed-form solution makes our proposed algorithms faster.
论文关键词：Symmetrical positive definite matrices,Log-Euclidean metric,Low Rank Representation,Subspace clustering
论文评审过程：Received 15 November 2016, Revised 26 June 2017, Accepted 5 July 2017, Available online 6 July 2017, Version of Record 8 January 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2017.07.009
