The appearance of dynamic scenes is often largely governed by a latent low-dimensional dynamic process. We show how to learn a mapping from video frames to this lowdimensional rep...
We present an online, recursive filtering technique to model linear dynamical systems that operate on the state space of symmetric positive definite matrices (tensors) that lie on...
This paper presents a new approachto recognizingmultiagent events observed by a static camera. To track objects robustly, knowledgeabout the groundplaneand the events is used. An ...
Many methods for motion computation and object tracking are based on the Lucas-Kanade (LK) framework [1]. We present a method which substantially speeds up the LK approach while p...
In order to summarize a video consisting of a sequence of different activities, there are three fundamental problems: tracking the objects of interest, detecting the activity chan...