PF-GNN: Differentiable particle filtering based approximation of universal graph representations.
Mohammed Haroon DuptyYanfei DongWee Sun LeePublished in: CoRR (2024)
Keyphrases
- particle filtering
- particle filter
- graph representations
- bayesian filtering
- visual tracking
- object tracking
- appearance model
- graph representation
- graph theory
- kalman filter
- graph structure
- closed form
- mean shift
- state space
- bayesian inference
- proposal distribution
- human motion
- objective function
- graph kernels
- moving objects
- markov random field
- high dimensional
- density function
- knn