Abstract. We address the problem of comparing sets of images for object recognition, where the sets may represent arbitrary variations in an object's appearance due to changin...
Human identification from gait is a challenging task in realistic surveillance scenarios in which people walking along arbitrary directions are shot by a single camera. In this pa...
As smartphones evolve researchers are studying new techniques to ease the human-mobile interaction. We propose EyePhone, a novel "hand-free" interfacing system capable o...
We propose a system that registers and retrieves text documents to annotate them on-line. The user registers a text document captured from a nearly top view and adds virtual annot...
We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...