Similarity-Based Pattern Recognition [electronic resource] : Third International Workshop, SIMBAD 2015, Copenhagen, Denmark, October 12-14, 2015. Proceedings /

A Novel Data Representation based on a Second-Order Dissimilarity Measure -- Characterizing Multiple Instance Datasets -- Supervised learning of diffiusion distance to improve histogram matching -- Similarity Analysis from Limiting Quantum Walks -- Introducing Negative Evidence in Ensemble Clustering -- Dissimilarity representations for low-resolution face recognition -- Deep metric learning using Triplet network -- Cluster Merging Based on Dominant Sets -- An Adaptive Radial Basis Function Kernel for Support Vector Data Description -- Robust initialization for learning Latent Dirichlet Allocation -- Unsupervised Motion Segmentation Using Metric Embedding of Features -- Transitive Assignment Kernels for Structural Classification -- Large scale Indefinite Kernel Fisher Discriminant -- Similarity-based User Identification across Social Networks -- Dominant-Set Clustering Using Multiple Affinity Matrices -- Distance-Based Network Recovery under Feature Correlation -- Discovery of salient low-dimensional dynamical structure using Hopfield Networks -- On Geodesic Exponential Kernels -- A Matrix Factorization Approach to Graph Compression -- A Geometrical Approach to Find Corresponding Patches in 3D Medical Surfaces -- Similarities, SDEs, and Most Probable Paths -- Can the optimum similarity matrix be selected before clustering for graph-based approaches? -- Approximate spectral clustering with utilized similarity information fusing geodesic based hybrid distance measures.

This book constitutes the proceedings of the Third International Workshop on Similarity Based Pattern Analysis and Recognition, SIMBAD 2015, which was held in Copenahgen, Denmark, in October 2015. The 15 full and 8 short papers presented were carefully reviewed and selected from 30 submissions.The workshop focus on problems, techniques, applications, and perspectives: from supervised to unsupervised learning, from generative to discriminative models, and from theoretical issues to empirical validations.