Attribute-based supervised deep learning model for action recognition

Chen, Kai, Ding, Guiguang and Han, Jungong (2017) Attribute-based supervised deep learning model for action recognition. Frontiers of Computer Science, 11 (2). pp. 219-229. ISSN 2095-2228

Full text not available from this repository. (Request a copy)

Abstract

Deep learning has been the most popular feature learning method used for a variety of computer vision applications in the past 3 years. Not surprisingly, this technique, especially the convolutional neural networks (ConvNets) structure, is exploited to identify the human actions, achieving great success. Most algorithms in existence directly adopt the basic ConvNets structure, which works pretty well in the ideal situation, e.g., under stable lighting conditions. However, its performance degrades significantly when the intra-variation in relation to image appearance occurs within the same category. To solve this problem, we propose a new method, integrating the semantically meaningful attributes into deep learning’s hierarchical structure. Basically, the idea is to add simple yet effective attributes to the category level of ConvNets such that the attribute information is able to drive the learning procedure. The experimental results based on three popular action recognition databases show that the embedding of auxiliary multiple attributes into the deep learning framework improves the classification accuracy significantly.

Item Type:	Article
Uncontrolled Keywords:	action recognition, convolutional neural network, attribute
Subjects:	G400 Computer Science
Department:	Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User:	Becky Skoyles
Date Deposited:	14 Mar 2017 15:47
Last Modified:	12 Oct 2019 20:46
URI:	http://nrl.northumbria.ac.uk/id/eprint/30080

Downloads