Research in Focus – Teaching Machines to See

Опубликовано 8 августа 2016, 22:03

Fei Fei Li, Associate Professor, Stanford University and Sebastian Nowozin, Researcher, Microsoft Research Cambridge. When we visually perceive the world, we intuitively recognize objects, scene categories, human motions—all sorts of semantically meaningful interpretations of what our eyes are taking in. Researchers are using highly flexible statistical models to teach computers to extract the meaningful information out of visual data and perform important visual tasks.