An assistant professor at Virginia Tech received close to $1 million “to teach machines to use ‘common sense’ in image analysis.”
Devi Parikh, who leads the Computer Vision Lab at Virginia Tech, is the recipient of the Allen Distinguished Investigator Award from the Paul G. Allen Family Foundation. She’s using the money to help computers “read” complex images with the use of cartoon clip art scenes.
“The visual world around us is bound by common sense laws depicting birds flying and balls moving once they’ve been kicked, but much of this knowledge is hidden from the eyes of a computer,” she said in a statement from the university.
“Simply labeling images with this information does not address the underlying problem of how it all fits together,” Parikh added. “We need a dense sampling of the visual world to understand how subtle changes in the scene can change its overall meaning.”
She believes that the best way to do so would be by using hundreds of thousands of Amazon Mechanical Turk workers online to showcase the visual world with clip art.
“These clip art scenes will serve as a completely new and rich test bed for computer vision researchers interested in solving high-level AI problems,” said Parikh. They may just be able to help computers develop a lexicon of common sense that will allow them to actually understand the visual world.
“Learning common sense will make our machines more accurate, reasonable and interpretable,” she said, which are “all imperative towards integrating artificial intelligence into our lives and society at large.”