This work investigates the use of nonlinear dependencies in natural image sequence statistics to learn higher-order structures in natural videos. We propose a two-layer model that...
The interpretation by a human of a scene in video material is heavily influenced by the context of the scene. As a result, researchers have recently made more use of context in th...
Ilias Kolonias, William J. Christmas, Josef Kittle...
Computer graphics as well as related disciplines often benefit from understanding the human visual system and its input. In this paper, we study statistical regularities of both ...
Visualizations of 3D spatial structures use various techniques such as user controlled interactions or 2D projection views to convey the structure to users. Researchers have shown...
We propose a novel approach for activity analysis in multiple synchronized but uncalibrated static camera views. In this paper, we refer to activities as motion patterns of objects...