Hybrid deep neural network model for human action recognition

Ijjina, E P and C, Krishna Mohan (2016) Hybrid deep neural network model for human action recognition. Applied Soft Computing, 46. pp. 936-952. ISSN 1568-4946

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


In this paper, we propose a hybrid deep neural network model for recognizing human actions in videos. A hybrid deep neural network model is designed by the fusion of homogeneous convolutional neural network (CNN) classifiers. The ensemble of classifiers is built by diversifying the input features and varying the initialization of the weights of the neural network. The convolutional neural network classifiers are trained to output a value of one, for the predicted class and a zero, for all the other classes. The outputs of the trained classifiers are considered as confidence value for prediction so that the predicted class will have a confidence value of approximately 1 and the rest of the classes will have a confidence value of approximately 0. The fusion function is computed as the maximum value of the outputs across all classifiers, to pick the correct class label during fusion. The effectiveness of the proposed approach is demonstrated on UCF50 dataset resulting in a high recognition accuracy of 99.68%.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Item Type: Article
Uncontrolled Keywords: Deep neural network; Convolutional neural network (CNN); Classifier fusion; Action bank features
Subjects: Computer science > Special computer methods
Computer science > Big Data Analytics
Divisions: Department of Computer Science & Engineering
Depositing User: Team Library
Date Deposited: 07 Sep 2015 04:37
Last Modified: 01 Sep 2017 09:07
URI: http://raiith.iith.ac.in/id/eprint/1909
Publisher URL: https://doi.org/10.1016/j.asoc.2015.08.025
OA policy: http://www.sherpa.ac.uk/romeo/issn/1568-4946/
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 1909 Statistics for this ePrint Item