C
Canyi Lu
Researcher at Carnegie Mellon University
Publications - 67
Citations - 6106
Canyi Lu is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Matrix norm & Rank (linear algebra). The author has an hindex of 30, co-authored 64 publications receiving 4484 citations. Previous affiliations of Canyi Lu include National University of Singapore & University of Science and Technology of China.
Papers
More filters
Journal ArticleDOI
Tensor Robust Principal Component Analysis with a New Tensor Nuclear Norm
TL;DR: Zhang et al. as mentioned in this paper proposed a tensor robust principal component analysis (TRPCA) model based on the tensor-tensor product (or t-product) to recover the low-rank and sparse components from their sum.
Book ChapterDOI
Robust and efficient subspace segmentation via least squares regression
TL;DR: This paper presents the Least Squares Regression (LSR) method for subspace segmentation, which takes advantage of data correlation, which is common in real data and significantly outperforms state-of-the-art methods.
Posted Content
Robust and Efficient Subspace Segmentation via Least Squares Regression
TL;DR: In this article, the Least Squares Regression (LSR) method was proposed for subspace segmentation, which takes advantage of data correlation and encourages a grouping effect which tends to group highly correlated data together.
Proceedings ArticleDOI
Tensor Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Tensors via Convex Optimization
TL;DR: This work proves that under certain suitable assumptions, it can recover both the low-rank and the sparse components exactly by simply solving a convex program whose objective is a weighted combination of the tensor nuclear norm and the l1-norm.
Journal ArticleDOI
Cross-Modal Retrieval With CNN Visual Features: A New Baseline
TL;DR: Off-the-shelf CNN visual features are extracted from the CNN model, which is pretrained on ImageNet with more than one million images from 1000 object categories, as a generic image representation to tackle cross-modal retrieval.