Kernelized Multiview Projection for Robust Action Recognition

Shao, Ling, Liu, Li and Yu, Mengyang (2016) Kernelized Multiview Projection for Robust Action Recognition. International Journal of Computer Vision, 118 (2). pp. 115-129. ISSN 0920-5691

art%3A10.1007%2Fs11263-015-0861-6.pdf - Published Version
Available under License Creative Commons Attribution 4.0.

Download (2MB) | Preview
Official URL:


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.

Item Type: Article
Uncontrolled Keywords: Human action recognition, Sequential distance learning, Multiple view fusion, Dimensionality reduction, Spectral coding
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Becky Skoyles
Date Deposited: 03 Nov 2015 10:22
Last Modified: 31 Jul 2021 13:34

Actions (login required)

View Item View Item


Downloads per month over past year

View more statistics