Sciweavers

Share
ICMCS
2006
IEEE

Visual Event Detection using Multi-Dimensional Concept Dynamics

10 years 5 months ago
Visual Event Detection using Multi-Dimensional Concept Dynamics
A novel framework is introduced for visual event detection. Visual events are viewed as stochastic temporal processes in the semantic concept space. In this concept-centered approach to visual event modeling, the dynamic pattern of an event is modeled through the collective evolution patterns of the individual semantic concepts in the course of the visual event. Video clips containing different events are classified by employing information about how well their dynamics in the direction of each semantic concept matches those of a given event. Results indicate that such a data-driven statistical approach is in fact effective in detecting different visual events such as exiting car, riot, and airplane flying.
Shahram Ebadollahi, Lexing Xie, Shih-Fu Chang, Joh
Added 11 Jun 2010
Updated 11 Jun 2010
Type Conference
Year 2006
Where ICMCS
Authors Shahram Ebadollahi, Lexing Xie, Shih-Fu Chang, John R. Smith
Comments (0)
books