We describe a system to learn an object template from a video stream, and localize and track the corresponding object in live video. The template is decomposed into a number of lo...
In this paper, we present a novel methodology to detect and recognize objects in cluttered scenes by proposing boosted contextual descriptors of landmarks in a framework of multi-...
Facial affect (or emotion) recognition is a central issue for many VMC and naturalistic computing applications. Most computational models assume "categorical perception"...
Diane J. Schiano, Sheryl M. Ehrlich, Kyle Sheridan
Abstract. In this paper, we develop a content-based video classification approach to support semantic categorization, high-dimensional indexing and multi-level access. Our contribu...
We present a model and an algorithm to detect salient regions in video taken from a moving camera. In particular, we are interested in capturing small objects that move independen...