학술논문
A multi-stage temporal pooling mechanism for video quality assessment
Document Type
Conference
Source
2016 50th Asilomar Conference on Signals, Systems and Computers Signals, Systems and Computers, 2016 50th Asilomar Conference on. :1853-1857 Nov, 2016
Subject
Language
Abstract
A multi-stage temporal pooling mechanism is proposed in this paper for improving the prediction capability of an objective quality metric for video quality assessment. The performance of the proposed pooling mechanism is evaluated along with that of traditional pooling mechanisms in terms of linear correlation coefficient and Spearman rank order correlation coefficient on four publicly available video quality databases. The experimental results demonstrate that the proposed pooling mechanism can significantly improve the prediction capability of an objective quality metric and can be adopted for predicting the video level quality scores of longer duration video sequences with time varying video qualities.