The proceedings contain 34 papers. The topics discussed include: a global method for reducing multidimensional size graphs; graph descriptors from B-matrix representation; dimensionality reduction for graph of words embedding; entropy versus heterogeneity for graphs; learning generative graph prototypes using simplified von Neumann entropy; information-geometric graph indexing from bags of partial node coverages; maximum likelihood for Gaussians on graphs; towards performance evaluation of graph-based representation; measuring the distance of generalized maps; aggregated search in graph databases: preliminary results; speeding up graph edit distance computation through fast bipartite matching; two new graph kernels and applications to chemoinformatics; parallel graduated assignment algorithm for multiple graph matching based on a common labeling; and smooth simultaneous structural graph matching and point-set registration.
Graph-Based Representations in Pattern Recognition
TORSELLO, Andrea
2011-01-01
Abstract
The proceedings contain 34 papers. The topics discussed include: a global method for reducing multidimensional size graphs; graph descriptors from B-matrix representation; dimensionality reduction for graph of words embedding; entropy versus heterogeneity for graphs; learning generative graph prototypes using simplified von Neumann entropy; information-geometric graph indexing from bags of partial node coverages; maximum likelihood for Gaussians on graphs; towards performance evaluation of graph-based representation; measuring the distance of generalized maps; aggregated search in graph databases: preliminary results; speeding up graph edit distance computation through fast bipartite matching; two new graph kernels and applications to chemoinformatics; parallel graduated assignment algorithm for multiple graph matching based on a common labeling; and smooth simultaneous structural graph matching and point-set registration.File | Dimensione | Formato | |
---|---|---|---|
2011-GBR-frontmatter.pdf
accesso aperto
Tipologia:
Documento in Post-print
Licenza:
Accesso gratuito (solo visione)
Dimensione
138.75 kB
Formato
Adobe PDF
|
138.75 kB | Adobe PDF | Visualizza/Apri |
I documenti in ARCA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.