Content-adaptive bitrate reduction in mobile multimedia applications

Grineko, Evgenia; Glasman, Konstantin; Belozertsev, Alexander

doi:10.1109/icce-berlin.2014.7034288

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parametric metrics estimate quality using only the information available at the receiver, like for example bitrate, frame rate, QP, motion vectors, and network information. These metrics are generally faster than pixel-based video quality metrics and, depending on the level of access to the bitstream, can produce reliable results [12]. It is worth pointing out that parametric metrics are coding and transmission dependent, reducing their applications.…”

Section: Introductionmentioning

confidence: 99%

A three layer system for audio-visual quality assessment

Martinez¹

2019

SIGMultimedia Rec.

View full text Add to dashboard Cite

The development of models for quality prediction of both audio and video signals is a fairly mature field. But, although several multimodal models have been proposed, the area of audiovisual quality prediction is still an emerging area. In fact, despite the reasonable performance obtained by combination and parametric metrics, currently there is no reliable pixel-based audiovisual quality metric. The approach presented in this work is based on the assumption that autoencoders, fed with descriptive audio and video features, might produce a set of features that is able to describe the complex audio and video interactions. Based on this hypothesis, we propose a set of multimedia quality metrics: video, audio and audiovisual. The visual features are natural scene statistics (NSS) and spatial-temporal measures of the video component. Meanwhile, the audio features are obtained by computing the spectrogram representation of the audio component. The model is formed by a 2-layer framework that includes an autoencoder layer and a classification layer. These two layers are stacked and trained to build the autoencoder network model. The model is trained and tested using a large set of stimuli, containing representative audio and video artifacts. The model performed well when tested against the UnB-AV and the LiveNetflix-II databases.

show abstract

Section: Introductionmentioning

confidence: 99%

A three layer system for audio-visual quality assessment

Martinez¹

2019

SIGMultimedia Rec.

View full text Add to dashboard Cite

show abstract

Content-adaptive bitrate reduction in mobile multimedia applications

Cited by 1 publication

References 6 publications

A three layer system for audio-visual quality assessment

A three layer system for audio-visual quality assessment

Contact Info

Product

Resources

About