CopVision learns its language from closed captioning subtitles transmitted in the TV signal. Everything that is said on COPS is kept in its memory to help it understand what it’s seeing. It analyzes every frame, searching the field for outlines that remind it of something it has seen before. When it recognizes a contour it tags it with a guess as to what might be going on, gathered from its experience of words and pictures that go together. It sometimes tries to put words in the mouths of the characters. When commercials come on, CopVision doesn’t know that it isn’t COPS, and it keeps watching the same way.
CopVision, like COPS, has no irony. It does its level best in every circumstance to do its duty.
Through projects like I Like to Watch / CopVision, it has become possible to imagine a day when automated media consumption can finally keep pace with digital production. Our machines may spare us the work of watching.