Ample evidence suggests that better machine learning models may be stead...
Bootstrapping labels from radiology reports has become the scalable
alte...
Acquiring high-quality annotations in medical imaging is usually a costl...
This work provides a strong baseline for the problem of multi-source
mul...
Obtaining datasets labeled to facilitate model development is a challeng...
Diagnostic imaging often requires the simultaneous identification of a
m...
The field of medical diagnostics contains a wealth of challenges which
c...
Theano is a Python library that allows to define, optimize, and evaluate...
We propose an approach to learn spatio-temporal features in videos from
...
The task of associating images and videos with a natural language descri...
We introduce a novel training principle for probabilistic models that is...
Recent progress in using recurrent neural networks (RNNs) for image
desc...
Generative Stochastic Networks (GSNs) have been recently introduced as a...
Recent work has shown how denoising and contractive autoencoders implici...