The aim of data mining is to find novel and actionable insights in data. However, most algorithms typically just find a single (possibly non-novel/actionable) interpretation of th...
We present a novel linear clustering framework (DIFFRAC) which relies on a linear discriminative cost function and a convex relaxation of a combinatorial optimization problem. The...
Constrained clustering has been well-studied for algorithms like K-means and hierarchical agglomerative clustering. However, how to encode constraints into spectral clustering rem...
This paper presents a system for graph clustering where users can visualize the clustering and give "hints" that help a computing method to find better solutions. Hints ...
We propose a flexible summarization framework for teamsport videos, which is able to integrate both the knowledge about displayed content (e.g. level of interest, type of view, et...