1 code implementation • journal 2021 • Qing Ding, Liquan Shen, Liangwei Yu, Hao Yang, Mai Xu
To overcome these limitations, we propose a patch-wise spatial-temporal quality enhancement network which firstly extracts spatial and temporal features, then recalibrates and fuses the obtained spatial and temporal features.
no code implementations • 2 Mar 2019 • Xuhao Jiang, Liquan Shen, Guorui Feng, Liangwei Yu, Ping An
In this paper, we propose a novel quadratic optimized model based on the deep convolutional neural network (QODCNN) for full-reference and no-reference screen content image (SCI) quality assessment.