Given an image sequence of a scene consisting of multiple rigidly moving objects, multi-body structure-and-motion (MSaM) is the task to segment the image feature tracks into the d...
Towards the goal of realizing a generic automatichuman activity recognition system, a new formalism is proposed. Activities are described by a chained hierarchical representation ...
1 We propose a novel video-based rendering algorithm with a single moving camera. We reconstruct a dynamic 3D model of the scene with a feature point set that "evolves" o...
Tracking articulated objects in image sequences remains a challenging problem, particularly in terms of the ability to localize the individual parts of an object given selfocclusi...
This paper deals with the fully automatic extraction of classifiable person features out of a video stream with challenging background. Basically the task can be split in two part...