Chinese online video platform company iQIYI has published a dataset of over half a million videos of 5,000 celebrities to foster the development of biometric recognition algorithms. iQIYI released the data as part of its Celebrity Video Identification Challenge. AI has made significant advancements in identifying humans in photos, but the different movements and expressions of people makes identification harder in videos. In addition, the challenge encourages participants to develop algorithms that not only identify individuals by their facial features, but also by the sound of their voice and their gait.
Developing Algorithms to Identify People in Videos
Michael McLaughlin is a research assistant at the Center for Data Innovation. He previously worked at Oracle and held internships at USA TODAY and in local government. Prior to joining the Center for Data Innovation, Michael graduated from Wake Forest University, where he majored in Communication with Minors in Politics and International Affairs and Journalism. He is currently pursuing his Master’s in Communication at Stanford University, specializing in Data Journalism.
View all posts by Michael McLaughlin