"Kernel"

Deep Blind Video Quality Assessment for User Generated Videos

As short video industry grows up, quality assessment of user generated videos has become a hot issue. Existing no reference video quality assessment methods are not suitable for this type of application scenario since they are aimed at synthetic …

GPU accelerated high-quality video/image super-resolution

This paper presents several novel GPU optimization technologies to accelerate the SRCNN(Super-Resolution Convolutional Neural Network) - one of the best super-resolution algorithm. We first directly parallelize and implement the SRCNN, then …

Hybrid center-symmetric local pattern for dynamic background subtraction

Effective foreground detection in dynamic scenes is a challenging task in computer vision applications. In this paper, we propose a novel background modeling method to tackle this problem. First, we propose a second-order center-symmetric local …