In this paper, we present an interactive offline tracking system for generic color objects. The system achieves 60100 fps on a 320 ? 240 video. The user can therefore easily refin...
Viewpoint invariant pedestrian recognition is an important yet under-addressed problem in computer vision. This is likely due to the difficulty in matching two objects with unknown...
We consider the problem of detecting a large number of different classes of objects in cluttered scenes. Traditional approaches require applying a battery of different classifier...
Antonio Torralba, Kevin P. Murphy, William T. Free...
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...
In this paper, we develop a general classification framework called Kullback-Leibler Boosting, or KLBoosting. KLBoosting has following properties. First, classification is based o...