Video Quality Assessment Using a Statistical Model of Human Visual Speed Perception

By Zhou Wang, Qiang Li. 2007

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. A. Bovik
2. Weisi Lin
3. Dacheng Tao
4. Luc Van Gool
5. Damon M. Chandler
6. Ming-Hsuan Yang
7. Zhou Wang
8. Qian Zhang

Citations in the corpus

• Scaling Autoregressive Video Models (2019, methodology): “However, these metrics were developed for images and have serious flaws when applied to videos (Wang et al., 2004a; Wang & Li, 2007; Zhang et al., 2018; Lee et al., 2018).”
• Video Quality Assessment by Reduced Reference Spatio-Temporal Entropic Differencing (2013, methodology): “Reference [16] is another RR VQA algorithm that calculates the weighted norm of the error in wavelet coefficients at selected locations to reduce the data required for quality computation.”
• From QoS to QoE: A Tutorial on Video Quality Assessment (2015, methodology): “In [90], the weighting function g ( x j , y j ) is defined based on the received information • Speed Weighted SSIM Different from a set of still images, the video sequence contains motion information, which is used to adjust the SSIM in [106].”
• Perceptual visual quality metrics: A survey (2011, background): “There have been continuing effort to combine spatial and temporal factors (spatiotemporal CSF formulation [68,177] and temporal error evaluation [4,116,168] in a better-grounded manner).”
• Information Content Weighting for Perceptual Image Quality Assessment (2011, methodology): “In [27], based upon statistical models of Bayesian motion perception [35], motion information content and perceptual uncertainty were computed for video quality assessment.”
• Objective Video Quality Assessment Methods: A Classification, Review, and Performance Comparison (2011, methodology): “In addition to the SSIM and the VSSIM, the MultiScale-SSIM (MS-SSIM) [51] and the Speed SSIM [52] metrics have been proposed.”
• F Mean Squared Error: Love It or Leave It? (2009, methodology): “For example, in [51], visual perception of motion is modeled using a recent psychophysical study of human visual speed perception [54] that has provided critical information about the prior and likelihood probability distributions of visual speed perception.”