Blind Prediction of Natural Video Quality

By Michele A. Saad, A. Bovik, Christophe Charrier. IEEE Transactions on Image Processing, 2014

479 citations recorded by the source corpus.

How researchers see this paper

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

Two-Level Approach for No-Reference Consumer Video Quality Assessment (2019, methodology): “In the field of NR-IQA and NR-VQA, Support Vector Regression (SVR) is the most commonly used regression model [5], [9], [38], [39], [43], but also neural networks and Random Forest Regression (RFR) have been employed successfully [7], [8], [12], [46].”
Quality Assessment of In-the-Wild Videos (2019, methodology): “content and may suffer from complex mixed real-world distortions that are temporally heterogeneous. On account of this, current state-of-the-art video quality assessment (VQA) methods (e.g., VBLIINDS [35] and VIIDEO [28]) validated on traditional synthetic VQA databases [30, 38] fail in predicting t”
Massive Online Crowdsourced Study of Subjective and Objective Picture Quality (2015, background): “…and controlling the perceptual effects of these distortions will require the development of powerful blind video quality assessment models, such as [53], and new VQA databases representative of human opinions of modern, realistic videos captured by current mobile video camera devices and…”
Large-Scale Study of Perceptual Video Quality (2018, methodology): “The NIQE [36] features were computed on non-overlapping blocks of size 96 × 96, then the computed NIQE distance is computed over frames and averaged over time, similar to how it was originally implemented in V-BLIINDS [38].”