B.: Occlusion patterns for object class detection

Despite the success of recent object class recognition systems, the long-standing problem of partial occlusion re-mains a major challenge, and a principled solution is yet to be found. In this paper we leave the beaten path of meth-ods that treat occlusion as just another source of noise – instead, we include the occluder itself into the modelling, by mining distinctive, reoccurring occlusion patterns from annotated training data. These patterns are then used as training data for dedicated detectors of varying sophistica-tion. In particular, we evaluate and compare models that range from standard object class detectors to hierarchical, part-based representations of occluder/occludee pairs. In an extensive evaluation we derive insights that can aid fur-ther developments in tackling the occlusion challenge. 1