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 describe a tracker that can track moving people in long sequences without manual initialization. Moving people are modeled with the assumption that, while configuration can var...
Neural activity appears to be a crucial component for shaping the receptive fields of cortical simple cells into adjacent, oriented subregions alternately receiving ON- and OFF-ce...
We present a dynamic inference algorithm in a globally parameterized nonlinear manifold and demonstrate it on the problem of visual tracking. An appearance manifold is usually non...
We present a novel method for jointly performing recognition of complex events and linking fragmented tracks into coherent, long-duration tracks. Many event recognition methods re...
Michael T. Chan, Anthony Hoogs, Rahul Bhotika, A. ...