This paper proposes a novel volume-based motion capture method using a bottom-up analysis of volume data and an example topology database of the human body. By using a two-step gra...
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...
This paper presents a virtual rap dancer that is able to dance to the beat of music coming in from music recordings, beats obtained from music, voice or other input through a micr...
Dennis Reidsma, Anton Nijholt, Ronald Poppe, Rutge...
Camera motion detection is essential for automated video analysis. We propose a new probabilistic model for detecting zoom-in/zoom-out operations. The model uses EM to estimate th...
—Salient areas in natural scenes are generally regarded as areas which the human eye will typically focus on, and finding these areas is the key step in object detection. In com...