An Open Source Platform for Perceived Video Quality Evaluation

Amour, Lamine; Souihi, Sami; Hoceini, Saïd; Mellouk, Abdelhamid

doi:10.1145/2815317.2815344

Cited by 7 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The algorithm presented in this paper was evaluated using two different datasets, built in the LiSSi laboratory to collect a lot of QoE IFs using a VLC media player, as illustrated in Table I [30].…”

Section: A Dataset Usedmentioning

confidence: 99%

Online QoE assessment model based on incremental stacked multiclass classifier

Elwerghemmi¹,

Heni²,

Ksantini³

et al. 2023

IJCDS

View full text Add to dashboard Cite

The enormous growth of streaming services in the last decade leads to the emergence of the Quality of Experience (QoE) metric, which aims to improve and optimize the delivery of video streaming service, thus strengthening the loyalty of end-users to the provided services. Yet, predicting QoE of a multimedia stream is a challenging task because it is dependent on several different influencing factors. Moreover, it should handle dynamic environments with large-scale data. Machine learning methods offer a method for quantifying the intricate connections between various influencing factors and QoE. Thus, in this paper, a new online QoE prediction method is proposed, namely, Incremental Stacked Support Vector Machine (ISSVM). The proposed approach uses a developed stacked generalization technique to increase the global accuracy and minimize the execution time, by combining predictions of several parallel Multi-class Incremental SVM (ISVM) learners trained with different types of sub-features. Then another ISVM model is used as a meta-classifier instead of a simple linear regression model in order to build a robust fully incremental model. In fact, using the ISVM model as weak classifiers aims to handle non-stationary and very huge volumes of data in real-time contexts. The findings show that the suggested model is more effective over the rest of the state-of-the-art methods.

show abstract

Section: A Dataset Usedmentioning

confidence: 99%

Online QoE assessment model based on incremental stacked multiclass classifier

Elwerghemmi¹,

Heni²,

Ksantini³

et al. 2023

IJCDS

View full text Add to dashboard Cite

show abstract

“…These crowdworkers get a small fee for the study, which is usually, like the recruitment, handled by a crowdsourcing provider like Microworkers 1 or Amazon Turk 2 . This methodology has been employed several times for obtaining video quality ratings [3,13,29]. Several studies have been conducted that researched the methodology, like the influence of video clip length [22], a training phase [23] and fraud detection [33].…”

Section: Assessment Of Video Quality In Video-conferencingmentioning

confidence: 99%

“…We first re-encoded the individual streams with ffmpeg. 3 The four individual stream were then composed to one clip with GStreamer 4 and the final result scaled to 1280 × 720 pixels and encoded with H264. This results in 16 different streamcompositions per videoclip.…”

Section: Preparation Of Materialsmentioning

confidence: 99%

The contrast effect: QoE of mixed video-qualities at the same time

2018

View full text Add to dashboard Cite

In desktop multi-party video-conferencing videostreams of participants are delivered in different qualities, but we know little about how such composition of the screen affects the quality of experience. Do the different videostreams serve as indirect quality references and the perceived video quality is thus dependent on other streams in the same session? How is the relation between the perceived qualities of each stream and the perceived quality of the overall session? To answer these questions we conducted a crowdsourcing study, in which we gathered over 5000 perceived quality ratings of overall sessions and individual streams. Our results show a contrast effect: high quality streams are rated better when more low quality streams are co-present, and vice versa. In turn, the quality perception of an overall session can increase significantly by exchanging one low quality stream with a high quality one. When comparing the means of individual and overall ratings we can further observe that users are more critical when asked for individual streams than for an overall rating. However, the results show that while contrast effect exists, the effect is not strong enough, to optimize the experience by lowering the quality of other participants.

show abstract

References

2023

Troubleshooting for Network Operators

View full text Add to dashboard Cite

An Open Source Platform for Perceived Video Quality Evaluation

Cited by 7 publications

References 5 publications

Online QoE assessment model based on incremental stacked multiclass classifier

Online QoE assessment model based on incremental stacked multiclass classifier

The contrast effect: QoE of mixed video-qualities at the same time

References

Contact Info

Product

Resources

About