One paper has been accepted by CVIU

Multiview Hessian Discriminative Sparse Coding for Image Annotation

W. Liu, D. Tao*, J. Cheng and Y. Tang

Abstract

Sparse coding represents a signal sparsely by using an overcomplete dictionary, and obtains promising performance in practical computer vision applications, especially for signal restoration tasks such as image denoising and image inpainting. In recent years, many discriminative sparse coding algorithms have been developed for classification problems, but they cannot naturally handle visual data represented by multiview features. In addition, existing sparse coding algorithms use graph Laplacian to model the local geometry of the data distribution. It has been identified that Laplacian regularization biases the solution towards a constant function which possibly leads to poor extrapolating power. In this paper, we present multiview Hessian discriminative sparse coding (mHDSC) which seamlessly integrates Hessian regularization with discriminative sparse coding for multiview learning problems. In particular, mHDSC exploits Hessian regularization to steer the solution which varies smoothly along geodesics in the manifold, and treats the label information as an additional view of feature for incorporating the discriminative power for image annotation. We conduct extensive experiments on PASCAL VOC'07 dataset and demonstrate the effectiveness of mHDSC for image annotation.

Keywords: Image annotation; Hessian; multiview; sparse coding

一论文被《模式识别与人工智能》录用

基于多分离部件稀疏编码的人脸图像分析

刘伟锋，刘红丽，王延江

摘要 考虑到不同部件（眼睛，嘴巴等）对人脸分析的贡献差别，提出基于多部件稀疏编码的人脸图像分析方法。首先，选取对人脸（表情）分析影响较大的几个人脸部件，然后利用多视角稀疏编码方法学习各部件的字典，并计算相应的稀疏编码，最后将稀疏编码输入分类器（支持向量机和最小均方误差）进行判决。分别在数据库JAFFE和Yale上进行了人脸（表情）识别以及有遮挡的人脸（表情）识别实验，实验结果表明，基于多部件稀疏编码的人脸分析能很好的调节各部件的权重，优于各单一部件和简单的多部件融合方法的性能。

IEEE SMC213 accepted papers are now available.

The accepted papers are now also available on the conference website:

 

http://www.smc2013.org/accepted_papers