1
Millions of blind and visually-impaired (BVI) people navigate urban environments every day, using smartphones for high-level …
Deep learning has thrived by training on large-scale datasets. However, in robotics applications sample efficiency is critical. We …
Single-view 3D shape reconstruction is an important but challenging problem, mainly for two reasons. First, as shape annotation is very …
We present a system for generating inconspicuous-looking textures that, when displayed in the physical world as digital or printed …
A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective. These …
Neural networks have become the state-of-the-art approach for machine translation (MT) in many languages. While …
In this work, we investigate the performance of untrained randomly initialized encoders in a general class of sequence to sequence …
Neural Module Networks, originally proposed for the task of visual question answering, are a class of neural network architectures that …
Deep Gaussian processes (DGP) have appealing Bayesian properties, can handle variable-sized data, and learn deep features. Their …
In partially observable environments, an agent’s policy should often be a function of the history of its interaction with the …