We propose a new approach for video event learning. The only hypothesis is the availability of tracked object attributes. The approach incrementally aggregates the attributes and r...
Despite significant progress in deformable model fitting over the last decade, the problem of efficient and accurate person-independentface fitting remains a challenging probl...
Discrete Wavelet Transform (DWT) is sensitive to the translation/shift of input signals, so its effectiveness could be negatively impacted when we encounter translation among sign...
Abstract. A human body measurement system using multiple viewpoints is proposed. Whole human body data taken from systems, which have been developed with a few viewpoints, have not...
In this article we present a novel fully automatic character segmentation for camera-based images. This is a top-down approach inspired by the human visual system: the high level ...