English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The development of audio-visual quality assessment models poses a number ofchallenges in order to obtain accurate predictions. One of these challenges isthe modelling of the complex interaction that audio and visual stimuli have andhow this interaction is interpreted by human users. The No-ReferenceAudio-Visual Quality Metric Based on a Deep Autoencoder (NAViDAd) deals withthis problem from a machine learning perspective. The metric receives two setsof audio and video features descriptors and produces a low-dimensional set offeatures used to predict the audio-visual quality. A basic implementation ofNAViDAd was able to produce accurate predictions tested with a range ofdifferent audio-visual databases. The current work performs an ablation studyon the base architecture of the metric. Several modules are removed orre-trained using different configurations to have a better understanding of themetric functionality. The results presented in this study provided importantfeedback that allows us to understand the real capacity of the metric'sarchitecture and eventually develop a much better audio-visual quality metric.

How deep is your encoder: an analysis of features descriptors for an autoencoder-based audio-visual quality metric