Jacob Whitehill

Papers

Total Citations

146

H-Index

About

Jacob Whitehill is a leading researcher at the intersection of computer vision, machine learning, and human-robot interaction, with a particular focus on affective computing and educational technology. His most influential work centers on head pose estimation, where he developed the *Generalized Adaptive View-based Appearance Model* (GAVAM)—a pioneering framework for monocular head pose estimation that has garnered nearly 100 citations. This work enabled accurate, real-time tracking of head position and orientation from a single camera, with critical applications in driver awareness systems and human-robot interaction. Whitehill’s contributions extend beyond vision; he has explored how robots can learn to teach more effectively through apprenticeship learning, using expert demonstrations to model pedagogical strategies such as timing and responsiveness. His research has been recognized for bridging the gap between low-level perception and high-level social interaction, making him a key figure in developing machines that can understand and respond to human behavior. With a career marked by impactful, interdisciplinary work, Whitehill continues to shape how computers perceive and interact with people in real-world settings.