Open AccessHuman Action Recognition Bases on Local Action Attributes
Author(s) -
Jing Zhang,
Hong Lin,
Weizhi Nie,
Lekha Chaisorn,
Yongkang Wong,
Mohan Kankanhalli
Publication year - 2015
Publication title -
journal of electrical engineering and technology/journal of electrical engineering and technology
Language(s) - English
Resource type - Journals
eISSN - 2093-7423
pISSN - 1975-0102
DOI - 10.5370/jeet.2015.10.3.1264
Subject(s) - action (physics) , discriminative model , computer science , artificial intelligence , construct (python library) , action recognition , feature (linguistics) , exploit , categorization , motion (physics) , domain (mathematical analysis) , pattern recognition (psychology) , machine learning , mathematics , class (philosophy) , physics , quantum mechanics , mathematical analysis , linguistics , philosophy , computer security , programming language
Human action recognition received many interest in the computer vision community. Most of the existing methods focus on either construct robust descriptor from the temporal domain, or computational method to exploit the discriminative power of the descriptor. In this paper we explore the idea of using local action attributes to form an action descriptor, where an action is no longer characterized with the motion changes in the temporal domain but the local semantic description of the action. We propose an novel framework where introduces local action attributes to represent an action for the final human action categorization. The local action attributes are defined for each body part which are independent from the global action. The resulting attribute descriptor is used to jointly model human action to achieve robust performance. In addition, we conduct some study on the impact of using body local and global low-level feature for the aforementioned attributes. Experiments on the KTH dataset and the MV-TJU dataset show that our local action attribute based descriptor improve action recognition performance.