p-Laplacian Regularized Sparse Coding for Human Activity Recognition

被引:103
作者
Liu, Weifeng [1 ]
Zha, Zheng-Jun [2 ]
Wang, Yanjiang [1 ]
Lu, Ke [3 ]
Tao, Dacheng [4 ,5 ]
机构
[1] China Univ Petr East China, Coll Informat & Control Engn, Qingdao 266580, Peoples R China
[2] Univ Sci & Technol China, Sch Informat Sci & Technol, Hefei 230026, Peoples R China
[3] Univ Chinese Acad Sci, Beijing 100049, Peoples R China
[4] Univ Technol Sydney, Ctr Quantum Computat & Intelligent Syst, Ultimo, NSW 2007, Australia
[5] Univ Technol Sydney, Fac Engn & Informat Technol, Ultimo, NSW 2007, Australia
基金
中国国家自然科学基金; 澳大利亚研究理事会;
关键词
Human activity recognition; manifold; p-Laplacian; sparse coding; DICTIONARY; ALGORITHM; SPACE; MODEL;
D O I
10.1109/TIE.2016.2552147
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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 (pLSC). 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, pLSC provides superior theoretical evidence than standard Laplacian regularized sparse coding with a proper p. We also provide a fast iterative shrinkage-thresholding algorithm for the optimization of pLSC. Finally, we input the sparse codes learned by the pLSC algorithm into support vector machines and conduct extensive experiments on the unstructured social activity attribute dataset and human motion database (HMDB51) for human activity recognition. The experimental results demonstrate that the proposed pLSC algorithm outperforms the manifold regularized sparse coding algorithms including the standard Laplacian regularized sparse coding algorithm with a proper p.
引用
收藏
页码:5120 / 5129
页数:10
相关论文
共 80 条
[1]   Human Activity Analysis: A Review [J].
Aggarwal, J. K. ;
Ryoo, M. S. .
ACM COMPUTING SURVEYS, 2011, 43 (03)
[2]   K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation [J].
Aharon, Michal ;
Elad, Michael ;
Bruckstein, Alfred .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2006, 54 (11) :4311-4322
[3]  
[Anonymous], 2013, Advances in neural information processing systems
[4]  
[Anonymous], 2011, P 1 INT C MULT RETR
[5]  
[Anonymous], 2009, P 26 ANN INT C MACH
[6]  
[Anonymous], 2006, Journal of the Royal Statistical Society, Series B
[7]  
[Anonymous], 2010, Proceedings of the 27th International Conference on International Conference on Machine Learning
[8]  
[Anonymous], 2008, 2008 IEEE C COMP VIS, DOI DOI 10.1109/CVPR.2008.4587652
[9]  
[Anonymous], 1993, SIGN SYST COMP 1993
[10]  
[Anonymous], 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition, DOI DOI 10.1109/CVPR.2008.4587408