We present a two-step method to speed-up object detection systems in computer vision that use Support Vector Machines (SVMs) as classifiers. In a first step we perform feature red...
Bernd Heisele, Thomas Serre, Sayan Mukherjee, Toma...
Here, we present a constrained object recognition task that has been robustly solved largely with simple machine learning methods, using a small corpus of about 100 images taken u...
This paper proposes a computational system of object categorization based on decomposition and adaptive fusion of visual information. A coupled Conditional Random Field is develop...
We describe a new paradigm for three-dimensional computer graphics, using projectors to graphically animate physical objects in the real world. The idea is to replace a physical o...
In the eld of computer vision, bene cial methods of measuring surface shape of transparent objects such as glasses have rarely been proposed. In this paper, we propose a convenien...