2015-07-20

Two papers are accepted by ICIMCS2015.

Sparse canonical correlation analysis for recognition 
 
ABSTRACT
Canonical correlation analysis (CCA) is one promising feature extraction and subspace learning method for multivariate vectors by exploiting the correlation between two multidimensional variables in a linear way. Hence CCA has been widely employed in many applications such as statistics, economics and signal processing. However, the traditional CCA may be difficult to interpret especially when the original variables are expected to involve only a few components. In this paper, we propose sparse canonical correlation analysis (SCCA) to overcome the above problem. SCCA can find a reasonable trade-off between statistical fidelity and interpretability. Furthermore, we use a generalized power method to optimize the proposed SCCA algorithm. And finally we conduct extensive experiments for recognition on several popular databases including UCI datasets and USAA dataset. Experimental results demonstrate that the proposed SCCA algorithm outperforms the traditional CCA algorithm.


Sparse Principle Motion Component for One-shot Gesture Recognition
 
ABSTRACT
With the rapid development of computer vision technology, gesture recognition has attracted much attention in recent years. However, the traditional gesture recognition methods waste a lot of time in the process of building a model with a large number of examples. To tackle the above problems, in this paper we propose sparse PCA based principle motion component (SPMC) method for one-shot gesture recognition, which can properly enhance recognition accuracy only with few training examples and unspecialized sensors. To evaluate the SPMC method, we conduct one-shot gesture recognition experiments on ChaLearn Gesture Dataset. Experimental results show that the proposed approach can improve the accuracy of gesture recognition.

Two paper are accepted by Neurocomputing Journal.

Hessian Regularization by Patch Alignment Framework

Abstract
In recent years, semi-supervised learning has played a key part in large-scale image management, where usually only a few images are labeled. To address this problem, many representative works have been reported, including transductive SVM, universum SVM, co-training and graph-based methods. The prominent method is the patch alignment framework, which unifies the traditional spectral analysis methods. In this paper, we propose Hessian regression based on the patch alignment framework. In particular, we construct a Hessian using the patch alignment framework and apply it to regression problems. To the best of our knowledge, there is no report on Hessian construction from the patch alignment viewpoint. Compared with the traditional Laplacian regularization, Hessian can better match the data and then leverage the performance. To validate the effectiveness of the proposed method, we conduct human face recognition experiments on a celebrity face dataset. The experimental results demonstrate the superiority of the proposed solution in human face classification.

Keywords—semi-supervised learning; Hessian; patch alignment; Least Squares


HSAE: A Hessian Regularized Sparse Auto-Encoders

Abstract
Auto-encoders are one kinds of promising non-probabilistic representation learning paradigms that can efficiently learn stable deterministic features. Recently, auto-encoder algorithms are drawing more and more attentions because of its attractive performance in learning insensitive representation with respect to data changes. The most representative auto-encoder algorithms are the regularized auto-encoders including contractive auto-encoder, denoising auto-encoders, and sparse auto-encoders. In this paper, we incorporate both Hessian regularization and sparsity constraints into auto-encoders and then propose a new auto-encoder algorithm called Hessian regularized sparse auto-encoders (HSAE). The advantages of the proposed HSAE lie in two folds: (1) it employs Hessian regularization to well preserve local geometry for data points; (2) it also efficiently extracts the hidden structure in the data by using sparsity constraints. Finally, we stack the single-layer auto-encoders and form a deep architecture of HSAE. To evaluate the effectiveness, we construct extensive experiments on the popular datasets including MNIST and CIFAR-10 dataset and compare the proposed HSAE with the basic auto-encoders, sparse auto-encoders, Laplacian auto-encoders and Hessian auto-encoders. The experimental results demonstrate that HSAE outperforms the related baseline algorithms.

Keywords: Hessian regularization; Sparse Representation; Auto-Encoder; Manifold