Improving Human Action Recognition through Hierarchical Neural Network Classifiers

Document Type

Conference Proceeding

Source of Publication

Proceedings of the International Joint Conference on Neural Networks

Publication Date

10-10-2018

Abstract

© 2018 IEEE. Automatic understanding of videos is one of the complex problems in machine learning and computer vision. An important area in the field of video analysis is human action recognition (HAR). Though a large number of HAR systems have already been developed, there is plenty of daily life actions that are difficult to recognize, due to several reasons, such as recording on different devices, poor video quality and similarities among actions. Development in the field of deep learning, especially in convolutional neural networks (CNN), has provided us with methods that are well-suited for the tasks of image and video recognition. This work implements a CNN-based hierarchical recognition approach to recognize 20 most difficult-to-recognize actions from the Kinetics dataset. Experimental results have shown that the application of our method significantly improves the quality of recognition for these actions.

ISBN

9781509060146

Publisher

Institute of Electrical and Electronics Engineers Inc.

Volume

2018-July

Last Page

7

Disciplines

Computer Sciences

Keywords

action recognition, neural networks

Scopus ID

85056540506

Indexed in Scopus

yes

Open Access

no

Link to Full Text

Share

COinS