Traditional sparse representation-based methods for human action recognition usually pool over the entire video to form the final feature representation, neglecting any spatio-temporal information of features. To employ spatio-temporal information, we present a novel histogram representation obtained by statistics on temporal changes of sparse coding coefficients frame by frame in the spatial pyramids constructed from videos. The histograms are further fed into a support vector machine with a spatial pyramid matching kernel for final action classification. We validate our method on two benchmarks, KTH and UCF Sports, and experiment results show the effectiveness of our method in human action recognition.
Yang LI
Chongqing University
Junyong YE
Chongqing University
Tongqing WANG
Chongqing University
Shijian HUANG
Chongqing University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Yang LI, Junyong YE, Tongqing WANG, Shijian HUANG, "Statistics on Temporal Changes of Sparse Coding Coefficients in Spatial Pyramids for Human Action Recognition" in IEICE TRANSACTIONS on Information,
vol. E98-D, no. 9, pp. 1711-1714, September 2015, doi: 10.1587/transinf.2015EDL8037.
Abstract: Traditional sparse representation-based methods for human action recognition usually pool over the entire video to form the final feature representation, neglecting any spatio-temporal information of features. To employ spatio-temporal information, we present a novel histogram representation obtained by statistics on temporal changes of sparse coding coefficients frame by frame in the spatial pyramids constructed from videos. The histograms are further fed into a support vector machine with a spatial pyramid matching kernel for final action classification. We validate our method on two benchmarks, KTH and UCF Sports, and experiment results show the effectiveness of our method in human action recognition.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2015EDL8037/_p
Copy
@ARTICLE{e98-d_9_1711,
author={Yang LI, Junyong YE, Tongqing WANG, Shijian HUANG, },
journal={IEICE TRANSACTIONS on Information},
title={Statistics on Temporal Changes of Sparse Coding Coefficients in Spatial Pyramids for Human Action Recognition},
year={2015},
volume={E98-D},
number={9},
pages={1711-1714},
abstract={Traditional sparse representation-based methods for human action recognition usually pool over the entire video to form the final feature representation, neglecting any spatio-temporal information of features. To employ spatio-temporal information, we present a novel histogram representation obtained by statistics on temporal changes of sparse coding coefficients frame by frame in the spatial pyramids constructed from videos. The histograms are further fed into a support vector machine with a spatial pyramid matching kernel for final action classification. We validate our method on two benchmarks, KTH and UCF Sports, and experiment results show the effectiveness of our method in human action recognition.},
keywords={},
doi={10.1587/transinf.2015EDL8037},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Statistics on Temporal Changes of Sparse Coding Coefficients in Spatial Pyramids for Human Action Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1711
EP - 1714
AU - Yang LI
AU - Junyong YE
AU - Tongqing WANG
AU - Shijian HUANG
PY - 2015
DO - 10.1587/transinf.2015EDL8037
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E98-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2015
AB - Traditional sparse representation-based methods for human action recognition usually pool over the entire video to form the final feature representation, neglecting any spatio-temporal information of features. To employ spatio-temporal information, we present a novel histogram representation obtained by statistics on temporal changes of sparse coding coefficients frame by frame in the spatial pyramids constructed from videos. The histograms are further fed into a support vector machine with a spatial pyramid matching kernel for final action classification. We validate our method on two benchmarks, KTH and UCF Sports, and experiment results show the effectiveness of our method in human action recognition.
ER -