A social camera is a camera carried or worn by a member of a social group, (e.g., a smartphone camera, a hand-held camcorder, or a wearable camera). These cameras are becoming increasingly immersed in our social lives and closely capture our social activities. In this talk, I argue that social cameras are the ideal sensors for social scene understanding, as they inherit social signals such as the gaze behavior of the people carrying them. I will present a computational representation for social scene understanding from social cameras. A social scene, in general, involves various human interactions in the form of visible social signals, such as body gestures, gaze directions, or facial expressions.
In the first part of my talk, I will show how these social signals can be recovered in 3D. This work includes 3D trajectory reconstruction and motion capture from body-mounted cameras. The second part of the talk will focus on how the reconstructed signals can discover social salience via a gaze concurrence analysis. Social salience is the 3D location of what people pay attention to and our method reconstructs the spatio-temporal structure of social salience that may occur in the social scene.
Hyun Soo Park is a Ph.D. student in Mechanical Engineering at Carnegie Mellon University under the supervision of Prof. Yaser Sheikh. He is interested in computer vision, graphics, and robotics. The main focus of his research is developing a computational basis for social scene understanding. He received his bachelor’s degree from POSTECH, Korea in 2007, and master’s degree from Carnegie Mellon University in 2009.