2017 · 44 citations · 26 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningGraph-based LearningRepresentation LearningSemantic NetworksBenchmark DatasetsGraph Representation LearningManifold LearningManifold RegularizationMulti-scale Graph RepresentationSemantic Knowledge RepresentationVisual AnnotationsVisual Knowledge Representation
We address zero-shot learning using a new manifold alignment framework based on a localized multi-scale transform on graphs. Our inference approach includes a smoothness criterion for a function mapping nodes on a graph (visual representation) onto a linear space (semantic representation), which we optimize using multi-scale graph wavelets. The robustness of the ensuing scheme allows us to operate with automatically generated semantic annotations, resulting in an algorithm that is entirely free of manual supervision, and yet improves the state-of-the-art as measured on benchmark datasets.
26
A tutorial on spectral clustering
Ulrike von Luxburg · Statistics and Computing · 2007 · 10.3K citations · Full text
On Spectral Clustering: Analysis and an algorithm
Andrew Y. Ng, Michael I. Jordan, Yair Weiss · 2001 · 7.8K citations
David I Shuman, Sunil K. Narang, Pascal Frossard et al. · IEEE Signal Processing Magazine · 2013 · 4.4K citations · Full text