How well do facial recognition algorithms cope with a million strangers?

In the last few years, several groups have announced that their facial recognition systems have achieved near-perfect accuracy rates, performing better than humans at picking the same face out of the crowd.

But those tests were performed on a dataset with only 13,000 images—fewer people than attend an average professional U.S. soccer game. What happens to their performance as those crowds grow to the size of a major U.S. city?