Study of Subjective and Objective Quality Assessment of Video

By Kalpana Seshadrinathan, Rajiv Soundararajan, A. Bovik, Lawrence K. Cormack. IEEE Transactions on Image Processing, 2010

1,231 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2fbc5ff6378caf42df5dc916cc92001e683fae56

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

Citations in the corpus

Blind Prediction of Natural Video Quality (2014, methodology): “…of a video is analyzed along the temporal dimension in two distinct ways: 1) By frame differencing: the statistics of frame differences are analyzed under the NVS model, and 2) By analyzing the types of motion occurring in the video and quantifying the motion in terms of a coherency measure.”
Analysis of Public Image and Video Databases for Quality Assessment (2012, neutral): “• LIVE Video Quality Database [34], [35].”
Video Quality Assessment by Reduced Reference Spatio-Temporal Entropic Differencing (2013, background): “Depending on the desired application and problem constraints, this framework of algorithms also allows users to pick any algorithm from the class of algorithms presented which meets the performance requirements and data rates required for quality computation.”
Video Quality Assessment on Mobile Devices: Subjective, Behavioral and Objective Studies (2012, methodology): “We believe that SS with hidden reference studies are preferable to longer double-stimulus (DS) studies [5], [6].”
Objective Video Quality Assessment Methods: A Classification, Review, and Performance Comparison (2011, methodology): “We independently conducted the evaluations of all metrics shown in Table IV, except for MOVIE for which we include the results from [93].”
MCL-JCV: A JND-based H.264/AVC video quality assessment dataset (2016, result): “As compared with image quality assessment datasets [14], existing video quality assessment datasets are rather limited in three aspects: the number of test sequences, the diversity of video contents, and the number of participating subjects.”
A reduced-reference perceptual image and video quality metric based on edge preservation (2012, neutral): “Finally, for video we consider the database in [25-27].”
Massive Online Crowdsourced Study of Subjective and Objective Picture Quality (2015, background): “Current legacy VQA databases, such as [54], [55] are useful tools but are limited in regard to content diversity, numbers of subjects, and distortion realism and variability.”
Large-Scale Study of Perceptual Video Quality (2018, methodology): “• 4 distorted videos drawn from the LIVE Video Quality Assessment Database [5], which we will refer to as the “golden videos.”
Peak signal-to-noise ratio revisited: Is simple beautiful? (2012, methodology): “For this study, we have identified two databases with a reasonable mix of different contents and relevant distortion types including source and channel artifacts: LIVE video quality database [2] and EPFL-PoliMi database [4].”
The Konstanz natural video database (KoNViD-1k) (2017, background): “Other databases similar to LIVE have been released such as IVP [20], CSIQ [21], MCL-V [22].”
Efficient Parallel Framework for HEVC Motion Estimation on Many-Core Processors (2014, methodology): “Although there are other video quality assessment approaches [40], the PSNR-based video quality measurement is widely used during the development of HEVC [41].”
Quality Assessment of In-the-Wild Videos (2019, background): “, VBLIINDS [35] and VIIDEO [28]) validated on traditional synthetic VQA databases [30, 38] fail in predicting the quality of in-the-wild videos [10, 23, 31, 42].”
UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2020, methodology): “Figure 6 displays the histogram of MOS distributions for the three UGC-VQA databases.”