— Bob Coyne and Richard Sproat

—WordsEye: An Automatic Text-to-Scene Conversion System (PDF)AT&T Labs — Research)

The text in the caption is what told the computer to assemble these objects in this order. Of course, someone had to tell the computer how to draw these objects, tag each object so that the computer knows where “in” an object is and where the “face” of an object is.

Via Grand Text Auto.