Zhang, Jingtian, Shum, Hubert P. H., Han, Jungong and Shao, Ling (2018) Action recognition from arbitrary views using transferable dictionary learning. IEEE Transactions on Image Processing, 27 (10). pp. 4709-4723. ISSN 1057-7149
Preview |
PDF (Published manuscript)
- Published Version
Available under License Creative Commons Attribution. Download (4MB) | Preview |
Abstract
Human action recognition is crucial to many practical applications, ranging from human-computer interaction to video surveillance. Most approaches either recognize the human action from a fixed view or require the knowledge of view angle, which is usually not available in practical applications. In this paper, we propose a novel end-to-end framework to jointly learn a view-invariance transfer dictionary and a view-invariant classifier. The result of the process is a dictionary that can project real-world 2D video into a view-invariant sparse representation, and a classifier to recognize actions with an arbitrary view. The main feature of our algorithm is the use of synthetic data to extract view-invariance between 3D and 2D videos during the pre-training phase. This guarantees the availability of training data, and removes the hassle of obtaining real-world videos in specific viewing angles. Additionally, for better describing the actions in 3D videos, we introduce a new feature set called the 3D dense trajectories to effectively encode extracted trajectory information on 3D videos. Experimental results on the IXMAS, N-UCLA, i3DPost and UWA3DII data sets show improvements over existing algorithms.
Item Type: | Article |
---|---|
Faculty \ School: | Faculty of Science > School of Computing Sciences |
Related URLs: | |
Depositing User: | LivePure Connector |
Date Deposited: | 20 Jul 2018 10:53 |
Last Modified: | 22 Oct 2022 03:58 |
URI: | https://ueaeprints.uea.ac.uk/id/eprint/67682 |
DOI: | 10.1109/TIP.2018.2836323 |
Downloads
Downloads per month over past year
Actions (login required)
![]() |
View Item |