This paper describes a domain independent approach to the use of genetic programming for object detection problems. Rather than using raw pixels or high level domain specific feat...
This paper presents a new approach for multi-view object class detection. Appearance and geometry are treated as separate learning tasks with different training data. Our approach...
— It is widely agreed that efficient visual search requires the integration of target-driven top-down information and image-driven bottom-up information. Yet the problem of gaze...
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-...
We propose a new method for detecting objects such as bags carried by pedestrians depicted in short video sequences. In common with earlier work on the same problem, the method sta...