arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.00920cs.MM
收藏

一种基于JND的视频质量评价模型及其应用

A JND-based Video Quality Assessment Model and Its Application

Haiqiang Wang, Xinfeng Zhang, Chao Yang, C. -C. Jay Kuo

摘要:

基于JND准则,最近构建了一个主观视频质量评估数据集,称为VideoSet。在这项工作中,我们提出了一个基于JND的VQA模型,使用概率框架来分析和清理收集到的主观测试数据。虽然大多数传统的VQA模型侧重于内容的可变性,我们提出的VQA模型同时考虑到主题和内容的可变性。通过求解最大似然估计(MLE)问题来联合优化用于描述主题和内容可变性的模型参数。作为一个应用,新的主观VQA模型被用来过滤不可靠的视频质量分数收集在VideoSet。最后通过实验验证了该模型的有效性。

英文摘要:

Based on the Just-Noticeable-Difference (JND) criterion, a subjective video quality assessment (VQA) dataset, called the VideoSet, was constructed recently. In this work, we propose a JND-based VQA model using a probabilistic framework to analyze and clean collected subjective test data. While most traditional VQA models focus on content variability, our proposed VQA model takes both subject and content variabilities into account. The model parameters used to describe subject and content variabilities are jointly optimized by solving a maximum likelihood estimation (MLE) problem. As an application, the new subjective VQA model is used to filter out unreliable video quality scores collected in the VideoSet. Experiments are conducted to demonstrate the effectiveness of the proposed model.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑