Merging chrominance and luminance in early, medium, and late fusion using Convolutional Neural Networks

By Miquel Perelló Nieto. 2015

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Dan Hendrycks
2. Kevin Gimpel
3. Yilun Du
4. Mohit Bansal
5. John Wieting
6. Percy Liang
7. Quoc V. Le
8. Yoshua Bengio

Citations in the corpus

• Early Methods for Detecting Adversarial Images (2016, background): “ceptible perturbations, whereas previously they were unnoticeable. Moreover, since converting from RGB to YUV is not destructive to the image, this simple form of protection has no impact on accuracy [7]. In sum, a neural network trained on YUV images will correspond to \fooling" images which a”