Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...
In this paper, we propose a novel dense depth recovery method for a trinocular video sequence. Specifically, we contribute a novel trinocular stereo matching model, which can eff...
Previous pixel-level change detection methods either contain a background updating step that is costly for moving cameras (background subtraction) or can not locate object positio...
We propose a 2D model-based approach for tracking human body parts during articulated motion. A human is modeled as a stick figure with thirteen landmarks, and an action is a sequ...
Abstract. Tracking is usually interpreted as finding an object in single consecutive frames. Regularization is done by enforcing temporal smoothness of appearance, shape and motio...
Markus Unger, Thomas Mauthner, Thomas Pock, Horst ...