Rectified linear unit (ReLU) is a widely used activation function for deep convolutional neural networks.
SCENE text recognition has attracted great interest from the academia and the industry in recent years owing to its importance in a wide range of applications.
Though a large body of computer vision research has investigated developing generic semantic representations, efforts towards developing a similar representation for 3D has been limited.
We propose a novel learning method to rectify document images with various distortion types from a single input image.
The stability of such algorithms is often improved with a warmup schedule for the learning rate.
Ranked #5 on Machine Translation on WMT2016 English-German