In this paper, we propose to use the Colored Pattern Appearance Model (CPAM) as a content representation for video scene break detection. This model represents a scene by means of...
—CENTRIST (CENsus TRansform hISTogram), a new visual descriptor for recognizing topological places or scene categories, is introduced in this paper. We show that place and scene ...
SenseCam is an automatic wearable camera, often seen as a tool for the creation of digital memories. In this paper, we report findings from a field trial in which SenseCams were w...
We explore the use of clouds as a form of structured lighting to capture the 3D structure of outdoor scenes observed over time from a static camera. We derive two cues that relate ...
In order to enable high-level semantics-based video annotation and interpretation, we tackle the problem of automatic decomposition of motion pictures into meaningful story units,...