Pretraining a neural network on a large dataset is becoming a cornerston...
In the last years, neural networks (NN) have evolved from laboratory
env...
Learning representations of neural network weights given a model zoo is ...
Learning representations of neural network weights given a model zoo is ...
Training large neural networks is possible by training a smaller hyperne...
In image generation, generative models can be evaluated naturally by vis...
Discovering a solution in a combinatorial space is prevalent in many
rea...
Deep learning has been successful in automating the design of features i...
Inferring objects and their relationships from an image is useful in man...
Scene graph generation (SGG) aims to predict graph-structured descriptio...
Graphs evolving over time are a natural way to represent data in many
do...
Graph Convolutional Networks (GCNs) are a class of general models that c...
We aim to better understand attention over nodes in graph neural network...
Spectral Graph Convolutional Networks (GCNs) are a generalization of
con...
In this paper we describe a solution to our entry for the emotion recogn...
In visual recognition tasks, such as image classification, unsupervised
...