An Efficient Temporal Model for Action Recognition Using Multivariate Linear Prediction
Date Issued
2012
Date
2012
Author(s)
Lin, Chin-An
Abstract
To recognize temporally extended actions, it is useful to introduce high-order temporal dependence into the recognition task. However, this will highly increase the computational complexity, when the commonly used graphical models such as HMM and CRF are employed. In this thesis, multivariate linear prediction is proposed to exploit high-order temporal dependence with lower computational complexity. In addition, our method makes no effort on defining and manually labeling states and can improve bag-of-word representations, which may contain considerable noise but has shown excellent performance in previous work. To show the applicability of the proposed method, we experiment not only on video datasets including KTH and UCF but on skeleton datasets such as MSR 3D action and UCF Kinect. In most of them, our method gets superior performance than the state-of-the-art methods.
Subjects
action recognition
multivariate linear prediction
temporal model
skeleton
time series
bag-of-word
video description
Type
thesis
File(s)![Thumbnail Image]()
Loading...
Name
ntu-101-R98942116-1.pdf
Size
23.32 KB
Format
Adobe PDF
Checksum
(MD5):00f388ea466d56287c38c4a0e5a6a75b