Current research trends in computer vision have tended towards achieving the goal of recognizing human action, due to the potential utility of such recognition in various applications. Among many potential approaches, an approach involving Gaussian Mixture Model (GMM) supervectors with a Support Vector Machine (SVM) and a nonlinear GMM KL kernel has been proven to yield improved performance for recognizing human activities. In this study, based on tensor analysis, we develop and exploit an extended class of action features that we refer to as gradient-flow tensor divergence. The proposed method has shown a best recognition rate of 96.3% for a KTH dataset, and reduced processing time.
Ngoc Nam BUI
Chonnam National University
Jin Young KIM
Chonnam National University
Hyoung-Gook KIM
Kwangwoon 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
Ngoc Nam BUI, Jin Young KIM, Hyoung-Gook KIM, "Gradient-Flow Tensor Divergence Feature for Human Action Recognition" in IEICE TRANSACTIONS on Fundamentals,
vol. E99-A, no. 1, pp. 437-440, January 2016, doi: 10.1587/transfun.E99.A.437.
Abstract: Current research trends in computer vision have tended towards achieving the goal of recognizing human action, due to the potential utility of such recognition in various applications. Among many potential approaches, an approach involving Gaussian Mixture Model (GMM) supervectors with a Support Vector Machine (SVM) and a nonlinear GMM KL kernel has been proven to yield improved performance for recognizing human activities. In this study, based on tensor analysis, we develop and exploit an extended class of action features that we refer to as gradient-flow tensor divergence. The proposed method has shown a best recognition rate of 96.3% for a KTH dataset, and reduced processing time.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E99.A.437/_p
Copy
@ARTICLE{e99-a_1_437,
author={Ngoc Nam BUI, Jin Young KIM, Hyoung-Gook KIM, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Gradient-Flow Tensor Divergence Feature for Human Action Recognition},
year={2016},
volume={E99-A},
number={1},
pages={437-440},
abstract={Current research trends in computer vision have tended towards achieving the goal of recognizing human action, due to the potential utility of such recognition in various applications. Among many potential approaches, an approach involving Gaussian Mixture Model (GMM) supervectors with a Support Vector Machine (SVM) and a nonlinear GMM KL kernel has been proven to yield improved performance for recognizing human activities. In this study, based on tensor analysis, we develop and exploit an extended class of action features that we refer to as gradient-flow tensor divergence. The proposed method has shown a best recognition rate of 96.3% for a KTH dataset, and reduced processing time.},
keywords={},
doi={10.1587/transfun.E99.A.437},
ISSN={1745-1337},
month={January},}
Copy
TY - JOUR
TI - Gradient-Flow Tensor Divergence Feature for Human Action Recognition
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 437
EP - 440
AU - Ngoc Nam BUI
AU - Jin Young KIM
AU - Hyoung-Gook KIM
PY - 2016
DO - 10.1587/transfun.E99.A.437
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E99-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 2016
AB - Current research trends in computer vision have tended towards achieving the goal of recognizing human action, due to the potential utility of such recognition in various applications. Among many potential approaches, an approach involving Gaussian Mixture Model (GMM) supervectors with a Support Vector Machine (SVM) and a nonlinear GMM KL kernel has been proven to yield improved performance for recognizing human activities. In this study, based on tensor analysis, we develop and exploit an extended class of action features that we refer to as gradient-flow tensor divergence. The proposed method has shown a best recognition rate of 96.3% for a KTH dataset, and reduced processing time.
ER -