3 papers
cs.LG2020
Error estimate for a universal function approximator of ReLU network with a local connection
Jae-Mo Kang, Sunghwan Moon
Neural networks have shown high successful performance in a wide range of tasks, but further studies are needed to improve its performance. We analyze the approximation error of th…
cs.CV2020
Deep Space-Time Video Upsampling Networks
Jaeyeon Kang, Younghyun Jo, Seoung Wug Oh +2
Video super-resolution (VSR) and frame interpolation (FI) are traditional computer vision problems, and the performance have been improving by incorporating deep learning recently.…
eess.IV2020
Learning the Loss Functions in a Discriminative Space for Video Restoration
Younghyun Jo, Jaeyeon Kang, Seoung Wug Oh +3
With more advanced deep network architectures and learning schemes such as GANs, the performance of video restoration algorithms has greatly improved recently. Meanwhile, the loss…