Back to Search Start Over

Class-specific sparse codes for representing activities

Authors :
Labeau, F
Thiran, J P
Umakanthan, Sabanadesan
Denman, Simon
Fookes, Clinton
Sridharan, Sridha
Labeau, F
Thiran, J P
Umakanthan, Sabanadesan
Denman, Simon
Fookes, Clinton
Sridharan, Sridha
Source :
Proceedings of the 2015 International Conference on Image Processing (ICIP)
Publication Year :
2015

Abstract

In this paper we investigate the effectiveness of class specific sparse codes in the context of discriminative action classification. The bag-of-words representation is widely used in activity recognition to encode features, and although it yields state-of-the art performance with several feature descriptors it still suffers from large quantization errors and reduces the overall performance. Recently proposed sparse representation methods have been shown to effectively represent features as a linear combination of an over complete dictionary by minimizing the reconstruction error. In contrast to most of the sparse representation methods which focus on Sparse-Reconstruction based Classification (SRC), this paper focuses on a discriminative classification using a SVM by constructing class-specific sparse codes for motion and appearance separately. Experimental results demonstrates that separate motion and appearance specific sparse coefficients provide the most effective and discriminative representation for each class compared to a single class-specific sparse coefficients.

Details

Database :
OAIster
Journal :
Proceedings of the 2015 International Conference on Image Processing (ICIP)
Notes :
application/pdf
Publication Type :
Electronic Resource
Accession number :
edsoai.on1146606952
Document Type :
Electronic Resource