Selecting User Generated Content for Use in Media Productions

This paper describes a video browsing tool for visual media production, enabling users to efficiently find relevant user generated content, while considering its relation to the professional content captured for the production. Users can iteratively cluster the content set by different features, and restrict the content set by selecting a subset of clusters, and perform similarity search. The tool supports metadata captured with the content (e.g., location, device) and provides support for extracting global and local visual features. Content with multiple views is supported.