YouTube SFV+HDR Quality Dataset

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Yilin, Yim, Joong Gon, Birkbeck, Neil, Adsumilli, Balu
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916296233320448
author Wang, Yilin
Yim, Joong Gon
Birkbeck, Neil
Adsumilli, Balu
author_facet Wang, Yilin
Yim, Joong Gon
Birkbeck, Neil
Adsumilli, Balu
contents The popularity of Short form videos (SFV) has grown dramatically in the past few years, and has become a phenomenal video category with billions of viewers. Meanwhile, High Dynamic Range (HDR) as an advanced feature also becomes more and more popular on video sharing platforms. As a hot topic with huge impact, SFV and HDR bring new questions to video quality research: 1) is SFV+HDR quality assessment significantly different from traditional User Generated Content (UGC) quality assessment? 2) do objective quality metrics designed for traditional UGC still work well for SFV+HDR? To answer the above questions, we created the first large scale SFV+HDR dataset with reliable subjective quality scores, covering 10 popular content categories. Further, we also introduce a general sampling framework to maximize the representativeness of the dataset. We provided a comprehensive analysis of subjective quality scores for Short form SDR and HDR videos, and discuss the reliability of state-of-the-art UGC quality metrics and potential improvements.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05305
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle YouTube SFV+HDR Quality Dataset
Wang, Yilin
Yim, Joong Gon
Birkbeck, Neil
Adsumilli, Balu
Computer Vision and Pattern Recognition
Multimedia
Image and Video Processing
The popularity of Short form videos (SFV) has grown dramatically in the past few years, and has become a phenomenal video category with billions of viewers. Meanwhile, High Dynamic Range (HDR) as an advanced feature also becomes more and more popular on video sharing platforms. As a hot topic with huge impact, SFV and HDR bring new questions to video quality research: 1) is SFV+HDR quality assessment significantly different from traditional User Generated Content (UGC) quality assessment? 2) do objective quality metrics designed for traditional UGC still work well for SFV+HDR? To answer the above questions, we created the first large scale SFV+HDR dataset with reliable subjective quality scores, covering 10 popular content categories. Further, we also introduce a general sampling framework to maximize the representativeness of the dataset. We provided a comprehensive analysis of subjective quality scores for Short form SDR and HDR videos, and discuss the reliability of state-of-the-art UGC quality metrics and potential improvements.
title YouTube SFV+HDR Quality Dataset
topic Computer Vision and Pattern Recognition
Multimedia
Image and Video Processing
url https://arxiv.org/abs/2406.05305