University of Oulu

Hajati F., Tavakolian M. (2020) Video Classification Using Deep Autoencoder Network. In: Barolli L., Hussain F., Ikeda M. (eds) Complex, Intelligent, and Software Intensive Systems. CISIS 2019. Advances in Intelligent Systems and Computing, vol 993. Springer, Cham.

Video classification using deep autoencoder network

Saved in:
Author: Hajati, Farshid1,2; Tavakolian, Mohammad3
Organizations: 1School of Information Technology and Engineering, MIT Sydney, Sydney, Australia
2College of Engineering and Science,Victoria University Sydney, Sydney, Australia
3Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 0.4 MB)
Persistent link:
Language: English
Published: Springer Nature, 2020
Publish Date: 2021-02-26


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.

see all

Series: Advances in intelligent systems and computing
ISSN: 2194-5357
ISSN-E: 2194-5365
ISSN-L: 2194-5365
ISBN: 978-3-030-22354-0
ISBN Print: 978-3-030-22353-3
Pages: 508 - 518
DOI: 10.1007/978-3-030-22354-0_45
Host publication: Complex, Intelligent, and Software Intensive Systems. CISIS 2019
Host publication editor: Barolli, L.
Ikeda, M.
Hussain, F. K.
Conference: Conference on Complex, Intelligent, and Software Intensive Systems
Type of Publication: A4 Article in conference proceedings
Field of Science: 113 Computer and information sciences
Copyright information: © Springer Nature Switzerland AG 2020. This is a post-peer-review, pre-copyedit version of an article published in Complex, Intelligent, and Software Intensive Systems. CISIS 2019. The final authenticated version is available online at: