Claudio Fanti

Learn More
Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the human motion model as a triangulated graph. Previous approaches learned models based just on positions and velocities of the body parts while ignoring their appearance. Moreover, a(More)
All Rights Reserved iii Acknowledgments I owe a great debt of gratitude to many people who have helped make the research work in this thesis possible. support, and encouragement throughout my years at Caltech. I am also grateful for his wisdom, understanding, and friendship for almost everything in life. It has been quite a pleasure working in the Learning(More)
Consider a number of moving points, where each point is attached to a joint of the human body and projected onto an image plane. Johannson showed that humans can effortlessly detect and recognize the presence of other humans from such displays. This is true even when some of the body points are missing (e.g. because of occlusion) and unrelated clutter(More)
  • 1