Diffusion Maps and Coarse-Graining: A Unified Framework for Dimensionality Reduction, Graph Partitioning, and Data Set Parameterization.
Stéphane LafonAnn B. LeePublished in: IEEE Trans. Pattern Anal. Mach. Intell. (2006)
Keyphrases
- diffusion maps
- graph partitioning
- dimensionality reduction
- data sets
- high dimensional data
- dimensionality reduction methods
- manifold learning
- nonlinear dimensionality reduction
- high dimensional
- low dimensional
- image segmentation
- graph model
- data clustering
- principal component analysis
- pattern recognition
- weighted graph
- feature extraction
- feature space
- spectral clustering
- unsupervised learning
- clustering algorithm
- principal components
- feature selection
- action classification
- dimension reduction
- high dimensionality
- data points
- linear discriminant analysis
- superpixels
- information theoretic
- semi supervised
- shape model
- shape prior
- sparse representation
- action recognition
- dimensional data
- image retrieval
- multiscale
- training data