We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...
Abstract. The exploitation of video data requires to extract information at a rather semantic level, and then, methods able to infer "concepts" from low-level video featu...
This paper describes experiments in human motion understanding, defined here as estimation of the physical state of the body (the Plant) combined with interpretation of that part ...
We introduce a physics-based model for 3D person tracking. Based on a biomechanical characterization of lower-body dynamics, the model captures important physical properties of bi...
Marcus A. Brubaker, David J. Fleet, Aaron Hertzman...
Abstract This paper proposes a Qualitative Normalised Templates (QNTs) framework for solving the human motion classification problem. In contrast to other human motion classifica...