Video Classification Using Deep Autoencoder Network
File version
Accepted Manuscript (AM)
Author(s)
Tavakolian, Mohammad
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Barolli, L
Hussain, FK
Ikeda, M
Date
Size
File type(s)
Location
Sydney, Australia
License
Abstract
We present a deep learning framework for video classification applicable to face recognition and dynamic texture recognition. A Deep Autoencoder Network Template (DANT) is designed whose weights are initialized by conducting unsupervised pre-training in a layer-wise fashion using Gaussian Restricted Boltzmann Machines. In order to obtain a class specific network and fine tune the weights for each class, the pre-initialized DANT is trained for each class of video sequences, separately. A majority voting technique based on the reconstruction error is employed for the classification task. The extensive evaluation and comparisons with state-of-the-art approaches on Honda/UCSD, DynTex, and YUPPEN databases demonstrate that the proposed method significantly improves the performance of dynamic texture classification.
Journal Title
Conference Title
Advances in Intelligent Systems and Computing
Book Title
Edition
Volume
993
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
© Springer Nature Switzerland AG 2020. This is the author-manuscript version of this paper. Reproduced in accordance with the copyright policy of the publisher.The original publication is available at www.springerlink.com
Item Access Status
Note
Access the data
Related item(s)
Subject
Nanotechnology
FACE RECOGNITION
REPRESENTATION
Persistent link to this record
Citation
Hajati, F; Tavakolian, M, Video Classification Using Deep Autoencoder Network, COMPLEX, INTELLIGENT, AND SOFTWARE INTENSIVE SYSTEMS (CISIS 2019), 2020, 993, pp. 508-518