.png){kind=icon}
返回
Human action recognition by feature-reduced Gaussian process classification
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patrec.2009.03.013.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper presents a spectral analysis-based feature-reduced Gaussian Processes (GP) classification approach to recognition of articulated and deformable human actions from image sequences. Using Tensor Subspace Analysis (TSA), space-time human silhouettes extracted from action sequences are transformed to a low dimensional multivariate time series, from which structure-based statistical features are extracted to summarize the action properties. GP classification, based oil spectrally reduced features, is then applied to learn and predict action categories. Experimental results on two real-world state-of-the-art datasets show that the GP classification outperforms a Support Vector Machine (SVM). In particular, spectral feature reduction can effectively eliminate the inconsistent features, while leaving performance undiminished. Moreover, compared with Automatic Relevance Determination (ARD), the spectral way for feature reduction is more efficient. (C) 2009 Elsevier B.V. All rights reserved.
Keyword:
Human action recognition
Characteristic-based descriptor
Gaussian process classification
Spectral feature reduction
期刊
IF:
3.3
论文数:
8.0K
被引数:
1.6W
机构
引用论文
Time Course and the Recanalization Rate of Superficial Vein Thrombosis Treated With Low-Molecular-Weight Heparin.png)
Angiology
AngiologyIF0
PREAI
分享收藏
没有更多内容
没有更多内容