— In this paper, we propose an original approach to control camera position and/or lighting conditions in an environment using image gradient information. Our goal is to ensure a...
Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
We propose algorithms and applications for using the hand as an interface device in virtual and physical spaces. In virtual drawing, by tracking the hand in 3D and estimating a vir...
We introduce a new large-scale video dataset designed to assess the performance of diverse visual event recognition algorithms with a focus on continuous visual event recognition ...
Sangmin Oh, Anthony Hoogs, A.G.Amitha Perera, Chia...
Recently, ToF-cameras have attracted attention because of their ability to generate a full 21 2 D depth image at video frame rates. Thus, ToF-cameras are suitable for real-time 3D...