Analyzing the performance of autoencoder-based objective quality metrics on audio-visual content

Files in This Item:
File Description SizeFormat 
insight_publication.pdf3.03 MBAdobe PDFDownload
Title: Analyzing the performance of autoencoder-based objective quality metrics on audio-visual content
Authors: Martinez, HelardFarias, Mylène C.Q.Hines, Andrew
Permanent link: http://hdl.handle.net/10197/11353
Date: 30-Jan-2020
Online since: 2020-04-29T14:57:27Z
Abstract: The development of audio-visual quality models faces a number of challenges, including the integration of audio and video sensory channels and the modeling of their interaction characteristics. Commonly, objective quality metrics estimate the quality of a single component (audio or video) of the content. Machine learning techniques, such as autoencoders, offer as a very promising alternative to develop objective assessment models. This paper studies the performance of a group of autoencoder-based objective quality metrics on a diverse set of audio-visual content. To perform this test, we use a large dataset of audio-visual content (The UnB-AV database), which contains degradations in both audio and video components. The database has accompanying subjective scores collected on three separate subjective experiments. We compare our autoencoder-based methods, which take into account both audio and video components (multi-modal), against several objective (single-modal) audio and video quality metrics. The main goal of this work is to verify the gain or loss in performance of these single-modal metrics, when tested on audio-visual sequences.
Funding Details: Science Foundation Ireland
metadata.dc.description.othersponsorship: Insight Research Centre
Type of material: Conference Publication
Publisher: Society for Imaging Science and Technology
Copyright (published version): 2020 Society for Imaging Science and Technology
Keywords: Audio qualityVideo qualityAutoencoderNo-reference quality metricAudio degradationsVideo degradations
DOI: 10.2352/ISSN.2470-1173.2020.9.IQSP-167
Language: en
Status of Item: Peer reviewed
Conference Details: The 2020 IS&T International Symposium on Electronic Imaging (EI2020), Burlingame, California, 26-30 January 2020
Appears in Collections:Computer Science Research Collection
Insight Research Collection

Show full item record

Page view(s)

117
Last Week
25
Last month
checked on Jun 7, 2020

Download(s)

27
checked on Jun 7, 2020

Google ScholarTM

Check

Altmetric


This item is available under the Attribution-NonCommercial-NoDerivs 3.0 Ireland. No item may be reproduced for commercial purposes. For other possible restrictions on use please refer to the publisher's URL where this is made available, or to notes contained in the item itself. Other terms may apply.