Devi Parikh

September 22, 2014 — Devi Parikh, Assistant Professor in the Bradley Department of Electrical and Computer Engineering at Virginia Tech, recently won a Google Faculty Research Award for her work on learning from visual abstractions. The award provides Parikh with $92,000 of unrestricted funds, and she and her graduate students will be able to work directly with Google researchers and engineers.

The Google awards are for one year and only full-time, tenure-track university faculty members are eligible. There are two award cycles per year, and recipients are selected through a comprehensive review process. For this award cycle, Google received 722 proposals from 44 countries; they funded 110 projects.

In her research on learning from visual abstractions, Parikh works from the idea that concepts that are difficult to describe textually may be easier to illustrate. By having thousands of online crowd workers manipulate clipart images to mimic photographs, she seeks to teach a computer to understand our visual world like humans do. “People are the best vision systems we have,” Parikh said. “If we can figure out a way for people to effectively teach machines, machines will be much more intelligent than they are today,” she said.

Parikh joined the department in 2013, where she is a core member of the Discovery Analytics Center and the Virginia Center for Autonomous Sytems (VaCAS); she also heads the Computer Vision Lab. She was granted a Google Faculty Research Award in 2012 for her research on relative attributes-based feedback for image search. She received a 2014 Young Investigator Program (YIP) award from the Army Research Office to support the development of transparent computer vision systems. She earned her master’s and doctorate in Electrical and Computer Engineering at Carnegie Mellon University in Pittsburgh, Pennsylvania, and previously worked as a Research Assistant Professor at the Toyota Technological Institute in Chicago.