Despite their recent success, deep neural networks continue to perform p...
Learning generative object models from unlabelled videos is a long stand...
Modern neural network architectures can leverage large amounts of data t...
Predicting the future trajectory of a moving agent can be easy when the ...
Contrastive learning allows us to flexibly define powerful losses by
con...
An important component for generalization in machine learning is to unco...
Learning data representations that are useful for various downstream tas...
When machine learning systems meet real world applications, accuracy is ...
Being able to spot defective parts is a critical component in large-scal...
While self-learning methods are an important component in many recent do...
Learning how to model complex scenes in a modular way with recombinable
...
In a previous work, it was shown that there is a curious problem with th...
Modern deep learning systems successfully solve many perception tasks su...
We describe the first method to automatically estimate the 3D pose of th...
Object class detection has been a synonym for 2D bounding box localizati...
While the majority of today's object class models provide only 2D boundi...