TIE paper entitled “p-Laplacian Regularized Sparse Coding for Human Activity Recognition” is online.

p-Laplacian Regularized Sparse Coding for Human Activity Recognition

Authors

W. Liu 

Weifeng Liu is with the College of Information and Control Engineering, China University of Petroleum (East China), Qingdao 266580, China (email: liuwf@ upc.edu.cn). 

Z. J. Zha ; Y. Wang ; K. Lu ; D. Tao

Abstract

Human activity analysis in videos has increasingly attracted attention in computer vision research with the massive number of videos now accessible online. Although many recognition algorithms have been reported recently, activity representation is challenging. Recently, manifold regularized sparse coding has obtained promising performance in action recognition, because it simultaneously learns the sparse representation and preserves the manifold structure. In this paper, we propose a generalized version of Laplacian regularized sparse coding for human activity recognition called p-Laplacian regularized sparse coding. The proposed method exploits p-Laplacian regularization to preserve the local geometry. The p-Laplacian is a nonlinear generalization of standard graph Laplacian and has tighter isoperimetric inequality. As a result, p-Laplacian regularized sparse coding provides superior theoretical evidence than standard Laplacian regularized sparse coding with a proper p. We also provide a fast iterative Shrinkage-Thresholding algorithm (FISTA) for the optimization of p-Laplacian regularized sparse coding. Lastly, we input the sparse codes learned by the p- Laplacian regularized sparse coding algorithm into support vector machines and conduct extensive experiments on the unstructured social activity attribute (USAA) dataset and human motion database (HMDB51) for human activity recognition. The experimental results demonstrate that the proposed p-Laplacian regularized sparse coding algorithm outperforms the manifold regularized sparse coding algorithms including the standard Laplacian regularized sparse coding algorithm with a proper p.

Keywords

human activity recognition

manifold

p-Laplacian

sparse coding

DOI:

10.1109/TIE.2016.2552147

One paper has been accepted on MMM2015.

Hessian regularized sparse coding for human action recognition

Abstract. With the rapid increase of online videos, recognition and search in videos becomes a new trend in multimedia computing. Action recognition in videos thus draws intensive research concerns recently. Second, sparse represen-tation has become state-of-the-art solution in computer vision because it has sev-eral advantages for data representation including easy interpretation, quick index-ing and considerable connection with biological vision. One prominent sparse representation algorithm is Laplacian regularized sparse coding (LaplacianSC). However, LaplacianSC biases the results toward a constant and thus results in poor generalization. In this paper, we propose Hessian regularized sparse coding (HessianSC) for action recognition. In contrast to LaplacianSC, HessianSC can well preserve the local geometry and steer the sparse coding varying linearly along the manifold of data distribution. We also present a fast iterative shrink-age-thresholding algorithm (FISTA) for HessianSC. Extensive experiments on human motion database (HMDB51) demonstrate that HessianSC significantly outperforms LaplacianSC and the traditional sparse coding algorithm for action recognition.

Keywords: Action recognition; sparse coding; Hessian regularization; manifold learning