This paper presents a new method to detect and accurately extract the moving object from a video sequence taken by a hand-held camera. In order to extract the high quality moving ...
We present a biologically-motivated system for the recognition of actions from video sequences. The approach builds on recent work on object recognition based on hierarchical feed...
Hueihan Jhuang, Thomas Serre, Lior Wolf, Tomaso Po...
An iterative method for reconstructing a 3D polygonal mesh and color texture map from multiple views of an object is presented. In each iteration, the method first estimates a tex...
This paper presents GeoS, a new algorithm for the efficient segmentation of n-dimensional image and video data. The segmentation problem is cast as approximate energy minimization ...
Automatically assigning keywords to images is of great interest as it allows one to index, retrieve, and understand large collections of image data. Many techniques have been propo...