The photo shows a baby, dressed in a striped shirt and denim overalls, staring intently at the toothbrush he is grasping in his left hand while he pokes at it with his right. The caption underneath reads, "A young boy is holding a baseball bat."
The computer at Stanford University in California that generated that description failed in this case, but in others its captions were much more accurate, if not terribly exciting. The phrases "black and white dog jumps over bar," "little girl is eating piece of cake," and "baseball player is throwing ball in game" are all correct characterizations of the photos in question. Even if it occasionally mistakes a toothbrush for a baseball bat, or a ferret for a cat, the computer today can do a much better job of explaining what is happening in a photograph than it could even a couple of years ago. The field of computer understanding of images has made remarkable progress in the last few years.
No entries found