Skip to main navigation Skip to search Skip to main content

Video Classification Using Deep Autoencoder Network

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationProceedings of the 13th International Conference on Complex, Intelligent, and Software Intensive Systems (CISIS-2019)
EditorsLeonard Barolli, Farookh Khadeer Hussain, Makoto Ikeda
Place of PublicationSwitzerland
PublisherSpringer Cham
Pages208-518
ISBN (Print)9783030223533, 9783030223540
DOIs
Publication statusPublished - 21 Jun 2019
EventCISIS 2019: The 13th International Conference on Complex, Intelligent, and Software Intensive Systems - University of Technology Sydney (UTS), Sydney, Australia, Sydney, Australia
Duration: 3 Jul 20195 Jul 2019

Publication series

NameAdvances in Intelligent Systems and Computing
NumberAISC993

Conference

ConferenceCISIS 2019: The 13th International Conference on Complex, Intelligent, and Software Intensive Systems
CitySydney, Australia
Period3/07/195/07/19

Fingerprint

Dive into the research topics of 'Video Classification Using Deep Autoencoder Network'. Together they form a unique fingerprint.

Cite this