Abstract— Man-made real-world environments are dominated by planar surfaces many of which constitute behaviorrelevant entities. Thus, the ability to perceive planar surfaces is v...
In this paper, we present a novel approach for human action recognition with histograms of 3D joint locations (HOJ3D) as a compact representation of postures. We extract the 3D sk...
This paper presents an online learning algorithm to construct from video sequences an image-based representation that is useful for recognition and tracking. For a class of object...
In this paper, we propose a framework that fuses multiple features for improved action recognition in videos. The fusion of multiple features is important for recognizing actions ...
To facilitate accurate and efficient detection of motion
patterns in video data, it is desirable to abstract from pixel
intensity values to representations that explicitly and co...