Abstract: For robots to perform a wide variety of tasks, they require a 3D representation of the world that is semantically rich, yet compact and efficient for task-driven perception and planning.

Abstract: Graph convolutional networks (GCNs) have become a powerful deep learning approach for graph-structured data. Different from traditional neural networks such as convolutional neural networks, ...

Microsoft's spreadsheet program can do way more than you might imagine. These are the hacks and tricks you need to know.