"AI for Accessibility"

Location: LTS Auditorium, 8080 Greenmead Drive

Speaker:
Hernisa Kacorri
Assistant Professor, College of Information Studies (iSchool)

Abstract:
Advances in artificial intelligence enable us to address key social issues. However, to see the benefit of this technology in many real-world applications, an integrative approach is necessary; effective solutions consist of a pipeline of processes or tasks involving both humans and machines.

My research has integrated human computer interaction (HCI) techniques and data-driven methods applied to human data to steer technological innovations for people with visual impairments and for people who are deaf or hard-of-hearing. In this talk, I will provide an overview of my research program, and I will demonstrate the effectiveness of integrating machine learning and HCI methodologies with two concrete examples: i) personal object recognizers trained by blind users, and ii) facial expression synthesis in sign language animations.

Speaker Bio:
Hernisa Kacorri is an assistant professor in the College of Information Studies (iSchool) and holds an affiliate appointment in the Department of Computer Science and the Human-Computer Interaction Lab (HCIL) at the University of Maryland, College Park.

Her research focuses on data-driven technologies that address human challenges, faced due to health or disability, with an emphasis on rigorous, user-based experimental methodologies to assess impact. Kacorri is a recipient of a Mina Rees Dissertation Fellowship in the Sciences, an ACM ASSETS best paper finalist and a best paper award, and a CHI honorable mention award. She has been recognized by the Rising Stars in EECS program of CMU/MIT.

Kacorri received her doctorate in computer science in 2016 from the Graduate Center at City University of New York, and has conducted research at National and Kapodistrian University of Athens, IBM Research-Tokyo, Lawrence Berkeley National Lab, and Carnegie Mellon University.