Video Quality Assessment and Machine Learning: Performance and Interpretability

Jacob Søgaard, Søren Forchhammer, Jari Korhonen

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

944 Downloads (Pure)

Abstract

In this work we compare a simple and a complex Machine Learning (ML) method used for the purpose of Video Quality Assessment (VQA). The simple ML method chosen is the Elastic Net (EN), which is a regularized linear regression model and easier to interpret. The more complex method chosen is Support Vector Regression (SVR), which has gained popularity in VQA research. Additionally, we present an ML-based feature selection method. Also, it is investigated how well the methods perform when tested on videos from other datasets. Our results show that content-independent cross-validation performance on a single dataset can be misleading and that in the case of very limited training and test data, especially in regards to different content as is the case for many video datasets, a simple ML approach is the better choice.
Original languageEnglish
Title of host publicationProceedings of IEEE QoMEX 2015.
Number of pages6
PublisherIEEE
Publication date2015
ISBN (Print)978-1-4799-8958-4
DOIs
Publication statusPublished - 2015
Event7th International Workshop on Quality of Multimedia Experience - Costa Navarino, Messinia, Greece
Duration: 26 May 201529 May 2015

Conference

Conference7th International Workshop on Quality of Multimedia Experience
CountryGreece
CityCosta Navarino, Messinia
Period26/05/201529/05/2015

Fingerprint Dive into the research topics of 'Video Quality Assessment and Machine Learning: Performance and Interpretability'. Together they form a unique fingerprint.

Cite this