In many real world prediction problems the output is a structured object like a sequence or a tree or a graph. Such problems range from natural language processing to computationa...
Shirish Krishnaj Shevade, Balamurugan P., S. Sunda...
This paper describes a new algorithm for recovering the
3D shape and motion of deformable and articulated objects
purely from uncalibrated 2D image measurements using an
iterati...
We develop an algorithm for finding and kinematically tracking multiple people in long sequences. Our basic assumption is that people tend to take on certain canonical poses, even...
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 ...
Motion estimation is known to be a non-convex optimization problem. This non-convexity comes from several ambiguities in motion estimation such as the aperture problem, or fast mo...