We present a computational approach to abnormal visual event detection, which is based on exploring and modeling local motion patterns in a non-linear subspace. We use motion vect...
A new algorithm is proposed for novel view generation in one-toone teleconferencing applications. Given the video streams acquired by two cameras placed on either side of a comput...
Antonio Criminisi, Jamie Shotton, Andrew Blake, Ph...
Change detection is one of the most commonly encountered low-level tasks in computer vision and video processing. A plethora of algorithms have been developed to date, yet no wide...
Nil Goyette, Pierre-Marc Jodoin, Fatih Porikli, Ja...
We propose a sequential Monte Carlo data association algorithm based on a two-level computational framework for tracking varying number of interacting objects in dynamic scene. Fi...
We present a discriminative approach to frame-by-frame head pose tracking that is robust to a wide range of illuminations and facial appearances and that is inherently immune to a...