We present a method for efficiently tracking objects represented as constellations of parts by integrating out the shape of the model. Parts-based models have been successfully ap...
Supervised learning of a parts-based model can be for-
mulated as an optimization problem with a large (exponen-
tial in the number of parts) set of constraints. We show how
thi...
M. Pawan Kumar, Andrew Zisserman, Philip H.S. Torr