Revisiting convolutional neural network on graphs with polynomial approximations of Laplace-Beltrami spectral filtering.
Shih-Gu HuangMoo K. ChungAnqi QiuAlzheimer's Disease Neuroimaging InitiativePublished in: CoRR (2020)
Keyphrases
- convolutional neural network
- laplace beltrami
- heat kernel
- spectral analysis
- graph laplacian
- face detection
- shape analysis
- point cloud
- basis functions
- shape descriptors
- graph structure
- riemannian manifolds
- euclidean space
- laplacian eigenmaps
- minimum spanning tree
- filter bank
- wiener filter
- d mesh
- geodesic distance
- data points
- speech signal
- linear combination