Sparse features have traditionally been tracked from frame to frame independently of one another. We propose a framework in which features are tracked jointly. Combining ideas fro...
One style of Multi-Engine Machine Translation architecture involves choosing the best of a set of outputs from different systems. Choosing the best translation from an arbitrary s...
Obtaining labeled data is a significant obstacle for many NLP tasks. Recently, online games have been proposed as a new way of obtaining labeled data; games attract users by being...
David Vickrey, Aaron Bronzan, William Choi, Aman K...
The ability to combine tactile, on-the-skin, sensory cues with the kinesthetic ones that widely available force-feedback devices are able to produce is a desirable one, opening th...
: Accurate and efficient video classification demands the fusion of multimodal information and the use of intermediate representations. Combining the two ideas into one framework, ...