Understanding Social Signals from Wearable Cameras

Goggles, wearable cameras are poised to enter our social spaces in a big way. In this talk, I will investigate what wearable cameras can tell us both about the person wearing the cameras and the people they interact with. In the first part, I will present a method to reconstruct the motion of a person from cameras mounted on different limbs of the person, with the goal of taking motion capture out of the lab or studio. In the second part, I will present a method that measure areas of social saliency from head-mounted cameras on different members of a social scene, with the goal of building robots that are truly collaborative partners rather than passive tools.

Joint work with Hyun Soo Park, Eakta Jain, Takaaki Shiratori, Leonid Sigal, and Jessica Hodgins. Research supported by NSF, Intel Research, Disney Research, and DARPA.

Contact Info: Nancy Lacson,

Yaser Sheikh is an Assistant Research Professor at the Robotics Institute, at Carnegie Mellon University. Prior to that, he was a postdoctoral fellow at CMU mentored by Takeo Kanade. He obtained his doctoral degree from the University of Central Florida in 2006 advised by Mubarak Shah. His research focus is in 3D understanding of scenes from images and its applications in media manipulation, robotic control, and activity understanding. He has won the Honda Initiation Award (2010), best paper awards at WACV (2012), SCA (2010), and ICCV THEMIS (2009), and the Hillman Fellowship for Excellence in Computer Science Research in 2004.