A multi-modal graphical model for robust recognition of group actions in meetings from disturbed videos.
Marc A. Al-HamesGerhard RigollPublished in: ICIP (3) (2005)
Keyphrases
- multi modal
- graphical models
- robust recognition
- audio visual
- conditional dependencies
- belief propagation
- video search
- probabilistic model
- random variables
- probabilistic graphical models
- human actions
- approximate inference
- human activities
- conditional random fields
- multi modality
- bayesian networks
- partial occlusion
- video sequences
- graph structure
- factor graphs
- high dimensional
- action recognition
- machine learning
- uni modal
- nonparametric belief propagation
- human motion
- video data
- high resolution
- spatio temporal
- viewpoint
- three dimensional
- feature selection