We develop a classification algorithm for hybrid autoregressive models of human motion for the purpose of videobased analysis and recognition. We assume that some temporal statist...
Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...
The ground truth labeling of an image dataset is a task that often requires a large amount of human time and labor. We present an infrastructure for distributed human labeling tha...
A Bayesian network formulation for relational shape matching is presented. The main advantage of the relational shape matching approach is the obviation of the non-rigid spatial m...
Anand Rangarajan, James M. Coughlan, Alan L. Yuill...
Recent research in object recognition has demonstrated the advantages of representing objects and scenes through localized patterns such as small image templates. In this paper we...