Humans do not perceive all parts of a scene with the same resolution, bu...
We introduce a video compression algorithm based on instance-adaptive
le...
We propose Skip-Convolutions to leverage the large amount of redundancie...
Most of the existing deep learning based end-to-end video coding (DLEC)
...
While most neural video codecs address P-frame coding (predicting each f...
Most of the existing deep learning based end-to-end image/video coding (...
We present PLONQ, a progressive neural image compression scheme which pu...
Neural data compression has been shown to outperform classical methods i...
When training end-to-end learned models for lossy compression, one has t...
Thanks to their improved data efficiency, equivariant neural networks ha...
Recent advances in deep generative modeling have enabled efficient model...
Media is generally stored digitally and is therefore discrete. Many
succ...
In this work, we propose a new recurrent autoencoder architecture, terme...
In this paper we present a a deep generative model for lossy video
compr...
In this proceeding we give an overview of the idea of covariance (or
equ...
The idea of equivariance to symmetry transformations provides one of the...
The manifold hypothesis states that many kinds of high-dimensional data ...
We propose a semantic segmentation model that exploits rotation and
refl...
Convolutional Neural Networks (CNNs) require a large amount of annotated...
Group equivariant and steerable convolutional neural networks (regular a...
The effectiveness of Convolutional Neural Networks stems in large part f...
Convolutional Neural Networks (CNNs) have become the method of choice fo...
This article presents the prediction difference analysis method for
visu...
It has long been recognized that the invariance and equivariance propert...
We present a method for visualising the response of a deep neural networ...
We introduce Group equivariant Convolutional Neural Networks (G-CNNs), a...
In a range of fields including the geosciences, molecular biology, robot...
When a three-dimensional object moves relative to an observer, a change
...