Talk by Alan Yuille, of UCLA. Given to the Redwood Center for Theoretical Neuroscience on April 8, 2010.
Abstract.
Recursive Compositional Models (RCMs) are class of hierarchical probabilistic models of images and objects. Visual structures are represented in a hierarchical form where complex structures are composed of more elementary structures following a design principle of recursive composition.
Probabilities are defined over these structures which exploit properties of the hierarchy (e.g. long range spatial relationships can be represented by local potentials at the upper levels of the hierarchy). The compositional nature of this representation enables efficient learning and inference algorithms. Hence the overall architecture of RCMs provides a balance between statistical and computational complexity.
We describe applications of these methods to a range of different vision problems. We show that the performance of these hierarchical methods is generally state of the art when evaluated on benchmarked datasets which validates the promise of this class of models.