Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the h...
We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models dire...
Without a deformation model, monocular 3D shape recovery of deformable surfaces is severly under-constrained. Even when the image information is rich enough, prior knowledge of th...
Visual interpretation of events requires both an appropriate representation of change occurring in the scene and the application of semantics for differentiating between different...
We present a probabilistic framework for recognizing objects in images of cluttered scenes. Hundreds of objects may be considered and searched in parallel. Each object is learned f...