TREC 2002 Video Track Experiments at MediaTeam Oulu and VTT.
Mika Rautiainen, Dmitri Vorobiev, Kai Noponen, Pertti Väyrynen, Matti Hosio, Esa Matinmikko, Timo Ojala, Tapio Seppänen, Jani Penttilä, Satu-Marja Mäkelä, Johannes Peltola · 2002
In TREC 2002 Video Track MediaTeam Oulu and VTT Technical Research Centre of Finland participated jointly in semantic feature extraction, manual search and interactive search tasks. In the semantic feature extraction task, we sent results for semantic categories of cityscape, landscape, people, speech and instrumental sound. Spario-temporal correlation of oriented gradient occurrences was used with example shots to detect shots containing people, cityscape or landscape. The audio signal features consisted of various statistical measurements and were used to detect shots containing speech or instrumental sound. Our video browsing and retrieval system, VIRE, was used for manual and interactive search tasks. Our system offers two techniques for video retrieval: 1. Multi-modal indexing based on self-organizing feature maps with semantic filtering. 2. An interactive navigating tool that combines two inter-shot properties, temporal coherency and metric similarities, into a view where database shots are presented in a lattice structure. We tested our interactive navigating tool with eight persons to obtain results for 25 pre-defined search topics. In this paper we give an overview of the approaches and a summary of the results.