Tran, HTM and Hogg, D orcid.org/0000-0002-6125-9564 (2017) Anomaly Detection using a Convolutional Winner-Take-All Autoencoder. In: Proceedings of the British Machine Vision Conference 2017. 28th British Machine Vision Conference, 04-07 Sep 2017, London, UK. British Machine Vision Association
Abstract
We propose a method for video anomaly detection using a winner-take-all convolutional autoencoder that has recently been shown to give competitive results in learning for classification task. The method builds on state of the art approaches to anomaly detection using a convolutional autoencoder and a one-class SVM to build a model of normality. The key novelties are (1) using the motion-feature encoding extracted from a convolutional autoencoder as input to a one-class SVM rather than exploiting reconstruction error of the convolutional autoencoder, and (2) introducing a spatial winner-take-all step after the final encoding layer during training to introduce a high degree of sparsity. We demonstrate an improvement in performance over the state of the art on UCSD and Avenue (CUHK) datasets.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2017, The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms. |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Depositing User: | Symplectic Publications |
Date Deposited: | 02 Oct 2017 16:16 |
Last Modified: | 08 May 2018 12:54 |
Published Version: | http://www.bmva.org/bmvc/?id=bmvc |
Status: | Published |
Publisher: | British Machine Vision Association |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:121891 |