The dictionary-aided sparse regression (SR) approach has recently emerged as a promising alternative to hyperspectral unmixing (HU) in remote sensing.
By assuming a human face as piece-wise planar surfaces, where each surface corresponds to a facial part, we develop in this paper a Constrained Part-based Alignment (CPA) algorithm for face recognition across pose and/or expression.
We then perform exact recovery analyses, and prove that the proposed greedy algorithm is robust to noise---including its identification of the (unknown) number of endmembers---under a sufficiently low noise level.
In this paper, we propose to combine SFA with deep learning techniques to learn hierarchical representations from the video data itself.
In this work, we propose a very simple deep learning network for image classification which comprises only the very basic data processing components: cascaded principal component analysis (PCA), binary hashing, and block-wise histograms.
Ranked #48 on Image Classification on MNIST
The task is to identify the inlier features and establish their consistent correspondences across the image set.
In particular, the single-sample face alignment accuracy is comparable to that of the well-known Deformable SRC algorithm using multiple gallery images per class.
Our framework is motivated by the observation that samples from the same class repetitively appear in the collection of ambiguously labeled training images, while they are just ambiguously labeled in each image.