Automatic semantic annotation of sports video requires that the domain knowledge is properly included and exploited in the annotation process and that low and intermediate-level f...
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 ...
In this paper, the rare event detection issue in video event detection is addressed through the proposed data mining framework which can be generalized to be domain independent. T...
In this work we present a novel two-layer hybrid Graphical model for combined shot and scene boundary detection in videos. In the first layer of the model, low-level features are...
Marc Al-Hames, Stefan Zettl, Frank Wallhoff, Steph...
In this paper we propose a novel video segmentation algorithm that is capable of reliably detecting both types of dissolves in addition to cuts and wipes based on the analysis of ...