Domains in which shapes of objects change rapidly and significantly are a challenge for existing representation techniques: sport is a good example of this. We present a texture-based approach that copes with these problems in addition to resolution variation. A set of exemplar poses are learned from subsampled example images of the target object, creating a set of multi-resolution template kernels which when convolved with the image respond suitably. This technique may then be used in established tracking algorithms (e.g. CONDENSATION [Contour tracking by shochastic propagation of conditional density]). We demonstrate the technique in two domains, and suggest a Markov approach using it to model behaviour.