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

    1157 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
    Country/TerritoryGreece
    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