We've all heard of DARPA, the Defense Advanced Research Projects Agency, and the agency just issued an announcement called The Mind's Eye which states:
"The Mind’s Eye program seeks to develop in machines a capability that currently exists only in animals: visual intelligence. Humans in particular perform a wide range of visual tasks with ease, which no current artificial intelligence can do in a robust way. Humans have inherently strong spatial judgment and are able to learn new spatiotemporal concepts directly from the visual experience. Humans can visualize scenes and objects, as well as the actions involving those objects. Humans possess a powerful ability to manipulate those imagined scenes mentally to solve problems. A machine‐based implementation of such abilities would be broadly applicable to a wide range of applications."
One of the purported uses of such a machine is a smart camera that possesses sufficient visual intelligence to report back on the activities in a given area of observation. In other words, the smart camera would be able to not only recognizes objects and their properties, the 'nouns' in a scene, but also apply reasoning to the actions, or 'verbs', in the scene and report back with a complete narrative on what was observed.