Semi-supervised action recognition in video via Labeled Kernel Sparse Coding and sparse L1 graph

► Labeled Kernel Sparse Coding. ► L1 Graph. ► Semi-supervised learning. ► Sparse representation. Recognizing human actions in a video sequence using small number of labeled data are very desirable in practical applications. In this paper an action recognition approach via Labeled Kernel Sparse Codin...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition letters Vol. 33; no. 14; pp. 1951 - 1956
Main Authors: Yang, Shuyuan, Wang, Xiuxiu, Yang, Lixia, Han, Yue, Jiao, Licheng
Format: Journal Article
Language:English
Published: Elsevier B.V 15.10.2012
Subjects:
Action recognition
Labeled Kernel Sparse Coding
Semi-supervised
Sparse L1 graph
Action recognition
Sparse L1 graph
Semi-supervised
Labeled Kernel Sparse Coding
ISSN:0167-8655, 1872-7344
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:► Labeled Kernel Sparse Coding. ► L1 Graph. ► Semi-supervised learning. ► Sparse representation. Recognizing human actions in a video sequence using small number of labeled data are very desirable in practical applications. In this paper an action recognition approach via Labeled Kernel Sparse Coding (LKSC) and sparse L1 graph is proposed under the framework of semi-supervised learning framework. Inspired by the fact that kernel trick can capture the nonlinear similarity of features, we extend the sparse representation classifier (SRC) is extended to the empirical kernel projection space. By using the calculated sparse coding coefficients of both labeled and unlabeled samples as the graph weights, a sparse L1 graph is established in a parameter-free manner. Some experiments are taken on Weizmann human action datasets and a movie sequence of a ballet dance, to investigate the performance of our proposed method, and the results show that it is insensitive to the only parameter σ, and can achieve high recognition rate when using some number of labeled samples.
ISSN:0167-8655
1872-7344
DOI:10.1016/j.patrec.2012.07.004