Action Recognition From Arbitrary Views Using Transferable Dictionary Learning

Zhang, Jingtian; Shum, Hubert P.H.; Han, Jungong; Shao, Ling

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.

Citation

Zhang, J., Shum, H. P., Han, J., & Shao, L. (2018). Action Recognition From Arbitrary Views Using Transferable Dictionary Learning. IEEE Transactions on Image Processing, 27(10), 4709-4723. https://doi.org/10.1109/tip.2018.2836323

• Journal Article Type: Article
• Acceptance Date: Apr 25, 2018
• Online Publication Date: May 15, 2018
• Publication Date: 2018-10
• Deposit Date: Sep 1, 2020
• Journal: IEEE Transactions on Image Processing
• Print ISSN: 1057-7149
• Electronic ISSN: 1941-0042
• Publisher: Institute of Electrical and Electronics Engineers
• Volume: 27
• Issue: 10
• Pages: 4709-4723
• DOI: https://doi.org/10.1109/tip.2018.2836323
• Public URL: https://durham-repository.worktribe.com/output/1293726