We propose a novel approach to understanding
activities from their partial observations monitored through
multiple non-overlapping cameras separated by unknown time
gaps. In our...
— In this paper, we introduce a high-speed vision platform, H3 (Hiroshima Hyper Human) Vision, which can simultaneously process a 1024× 1024 pixel image at 1000 fps and a 256× ...
This paper presents a robust face detector under partial occlusion. In recent years, the effectiveness of Support Vector Machine (SVM) to object detection is reported. However, co...
This paper presents a method for prototyping grasp-sensitive surfaces using optical fibers. In this system one end of a fiber bundle is attached to an image sensor. The other en...
Content-based classification of audio data is an important problem for various applications such as overall analysis of audio-visual streams, boundary detection of video story se...