Team develops vision system that improves object recognition

A research group at Disney Research Pittsburgh has developed a computer vision system that, much like humans, can continuously improve its ability to recognize objects by picking up hints while watching videos.

Teaching computers to see—by learning to see like computers

Object-recognition systems—software that tries to identify objects in digital images—typically rely on machine learning. They comb through databases of previously labeled images and look for combinations of visual features ...

page 1 from 3