Kernelized Multiview Projection for Robust Action Recognition.

Saved in:

Bibliographic Details
Title:	Kernelized Multiview Projection for Robust Action Recognition.
Authors:	Shao, Ling¹ ling.shao@ieee.org, Liu, Li¹ li2.liu@northumbria.ac.uk, Yu, Mengyang¹ m.y.yu@ieee.org
Source:	International Journal of Computer Vision. Jun2016, Vol. 118 Issue 2, p115-129. 15p.
Subjects:	Mathematical models of human behavior, Kernel (Mathematics), Kernel functions, Distance education research, Semantics, Mathematical models
Abstract:	Conventional action recognition algorithms adopt a single type of feature or a simple concatenation of multiple features. In this paper, we propose to better fuse and embed different feature representations for action recognition using a novel spectral coding algorithm called Kernelized Multiview Projection (KMP). Computing the kernel matrices from different features/views via time-sequential distance learning, KMP can encode different features with different weights to achieve a low-dimensional and semantically meaningful subspace where the distribution of each view is sufficiently smooth and discriminative. More crucially, KMP is linear for the reproducing kernel Hilbert space, which allows it to be competent for various practical applications. We demonstrate KMP's performance for action recognition on five popular action datasets and the results are consistently superior to state-of-the-art techniques. [ABSTRACT FROM AUTHOR]
	Copyright of International Journal of Computer Vision is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	Conventional action recognition algorithms adopt a single type of feature or a simple concatenation of multiple features. In this paper, we propose to better fuse and embed different feature representations for action recognition using a novel spectral coding algorithm called Kernelized Multiview Projection (KMP). Computing the kernel matrices from different features/views via time-sequential distance learning, KMP can encode different features with different weights to achieve a low-dimensional and semantically meaningful subspace where the distribution of each view is sufficiently smooth and discriminative. More crucially, KMP is linear for the reproducing kernel Hilbert space, which allows it to be competent for various practical applications. We demonstrate KMP's performance for action recognition on five popular action datasets and the results are consistently superior to state-of-the-art techniques. [ABSTRACT FROM AUTHOR]
ISSN:	09205691
DOI:	10.1007/s11263-015-0861-6