The way an object looks and sounds provide complementary reflections of ...
Sustained contact interactions like scraping and rolling produce a wide
...
We introduce a visually-guided and physics-driven task-and-motion planni...
We introduce ThreeDWorld (TDW), a platform for interactive multi-modal
p...
Encouraged by the success of deep neural networks on a variety of visual...
Segmenting objects in images and separating sound sources in audio are
c...
We introduce PixelPlayer, a system that, by leveraging large amounts of
...
Objects make distinctive sounds when they are hit or scratched. These so...