While improving prediction accuracy has been the focus of machine learning in recent years,
this alone does not suffice for reliable decision-making. Deploying learning systems in …

Video captioning is an automated collection of natural language phrases that explains the
contents in video frames. Because of the incomparable performance of deep learning in the …

We present a system which can recognize the contents of your meal from a single image,
and then predict its nutritional contents, such as calories. The simplest version assumes that …

Machine learning applications such as finance and medicine demand accurate and
justifiable predictions, barring most deep learning methods from use. In response, previous …

In image classification, visual separability between different object categories is highly
uneven, and some categories are more difficult to distinguish than others. Such difficult …

The wealth of structured (eg Wikidata) and unstructured data about the world available today
presents an incredible opportunity for tomorrow's Artificial Intelligence. So far, integration of …

Despite a recent push towards large-scale object recognition, activity recognition remains
limited to narrow domains and small vocabularies of actions. In this paper, we tackle the …

Abstract We introduce Dynamic Deep Neural Networks (D2NN), a new type of feed-forward
deep neural network that allows selective execution. Given an input, only a subset of D2NN …

We present a new tree based approach to composing expressive image descriptions that
makes use of naturally occuring web images with captions. We investigate two related tasks …

Abstract Reasoning about objects and their affordances is a fundamental problem for visual
intelligence. Most of the previous work casts this problem as a classification task where …