We propose a novel approach for modelling correlations
between activities in a busy public space captured by multiple
non-overlapping and uncalibrated cameras. In our approach,
...
Chen Change Loy (Queen Mary, University of London)...
Our goal is to segment a video sequence into moving objects and the world scene. In recent work, spectral embedding of point trajectories based on 2D motion cues accumulated from ...
Computation in the physical world is restricted by the following spatial locality constraint: In a single unit of time, information can only travel a bounded distance in space. A ...
Non-rigid object detection and articulated pose estimation
are two related and challenging problems in computer
vision. Numerous models have been proposed over the
years and oft...
Mykhaylo Andriluka (TU Darmstadt), Stefan Roth (TU...
Most modern computer vision systems for high-level
tasks, such as image classification, object recognition and
segmentation, are based on learning algorithms that are
able to se...