We introduce an approach to accurately detect and segment partially occluded objects in various viewpoints and scales. Our main contribution is a novel framework for combining obj...
: This paper presents a novel representation for three-dimensional objects in terms of affine-invariant image patches and their spatial relationships. Multi-view constraints associ...
Fred Rothganger, Svetlana Lazebnik, Cordelia Schmi...
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 ...