We develop hierarchical, probabilistic models for objects, the parts composing them, and the visual scenes surrounding them. Our approach couples topic models originally developed...
Erik B. Sudderth, Antonio Torralba, William T. Fre...
Weakly supervised discovery of common visual structure in highly variable, cluttered images is a key problem in recognition. We address this problem using deformable part-based mo...
We describe a hierarchical probabilistic model for the detection and recognition of objects in cluttered, natural scenes. The model is based on a set of parts which describe the e...
Erik B. Sudderth, Antonio B. Torralba, William T. ...
Abstract. Images rendered with traditional computer graphics techniques, such as scanline rendering and ray tracing, appear focused at all depths. However, there are advantages to ...
Brian A. Barsky, Daniel R. Horn, Stanley A. Klein,...
Abstract. In the context of the RoboCup Simulation League, we describe a new representation of a software agent’s visual perception (“scene”), well suited for case-based reas...