No-Reference Video Quality Assessment by Multilayer Selected Deep Features and Neural Networks

In this work, we propose a general-purpose no-reference (NR) video quality assessment (VQA) metric based on the cascade combination of 2D convolutional neural network (CNN), multi-layer perceptron (MLP), and support vector regression (SVR) model. The features are extracted from both spatial and spatiotemporal domains by using a 2D CNN. These features can capture different aspects of video frames. We take these features as inputs of the MLP to obtain estimated quality scores on different perspectives. Finally, these quality scores are combined as a final quality score by an SVR model. The proposed method is evaluated on the well-known LIVE Video quality database with other state-of-the-art VQA metrics. And the experimental result demonstrates that our method is competitive with other full-reference and NR VQA metrics.