This paper presents a top-down approach to 3D data analysis by fitting a Morphable Model to scans of faces. In a unified framework, the algorithm optimizes shape, texture, pose an...
We present a hierarchical feature fusion model for image classification that is constructed by an evolutionary learning algorithm. The model has the ability to combine local patch...
Fabien Scalzo, George Bebis, Mircea Nicolescu, Lea...
This work is about scene interpretation in the sense of detecting and localizing instances from multiple object classes. We concentrate on object indexing: generate an over-comple...
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
Schematic tables are a new representation for conditionals. Roughly a cross between decision tables and data flow graphs, they represent computation and decision-making orthogona...