Head action recognition, as a specific problem in action recognition, has been studied in this paper. Different from most existing researches, our head action recognition problem is specifically defined for the requirement of some practical applications. Based on our definition, we build a corresponding head action dataset which contains many challenging cases. For action recognition, we proposed a real-time head action recognition framework based on HOF and ELM. The framework consists of face detection based ROI determination, HOF feature extraction in ROI, and ELM based action prediction. Experiments show that our method achieves good accuracy and is efficient enough for practical applications.
Tie HONG
National University of Defense Technology
Yuan Wei LI
Zhejiang Normal University
Zhi Ying WANG
National University of Defense Technology
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
Tie HONG, Yuan Wei LI, Zhi Ying WANG, "Real-Time Head Action Recognition Based on HOF and ELM" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 1, pp. 206-209, January 2019, doi: 10.1587/transinf.2018EDL8191.
Abstract: Head action recognition, as a specific problem in action recognition, has been studied in this paper. Different from most existing researches, our head action recognition problem is specifically defined for the requirement of some practical applications. Based on our definition, we build a corresponding head action dataset which contains many challenging cases. For action recognition, we proposed a real-time head action recognition framework based on HOF and ELM. The framework consists of face detection based ROI determination, HOF feature extraction in ROI, and ELM based action prediction. Experiments show that our method achieves good accuracy and is efficient enough for practical applications.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDL8191/_p
Copy
@ARTICLE{e102-d_1_206,
author={Tie HONG, Yuan Wei LI, Zhi Ying WANG, },
journal={IEICE TRANSACTIONS on Information},
title={Real-Time Head Action Recognition Based on HOF and ELM},
year={2019},
volume={E102-D},
number={1},
pages={206-209},
abstract={Head action recognition, as a specific problem in action recognition, has been studied in this paper. Different from most existing researches, our head action recognition problem is specifically defined for the requirement of some practical applications. Based on our definition, we build a corresponding head action dataset which contains many challenging cases. For action recognition, we proposed a real-time head action recognition framework based on HOF and ELM. The framework consists of face detection based ROI determination, HOF feature extraction in ROI, and ELM based action prediction. Experiments show that our method achieves good accuracy and is efficient enough for practical applications.},
keywords={},
doi={10.1587/transinf.2018EDL8191},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Real-Time Head Action Recognition Based on HOF and ELM
T2 - IEICE TRANSACTIONS on Information
SP - 206
EP - 209
AU - Tie HONG
AU - Yuan Wei LI
AU - Zhi Ying WANG
PY - 2019
DO - 10.1587/transinf.2018EDL8191
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2019
AB - Head action recognition, as a specific problem in action recognition, has been studied in this paper. Different from most existing researches, our head action recognition problem is specifically defined for the requirement of some practical applications. Based on our definition, we build a corresponding head action dataset which contains many challenging cases. For action recognition, we proposed a real-time head action recognition framework based on HOF and ELM. The framework consists of face detection based ROI determination, HOF feature extraction in ROI, and ELM based action prediction. Experiments show that our method achieves good accuracy and is efficient enough for practical applications.
ER -