TOSCA-MP at Search and Hyperlinking of Television Content Task
Publikation aus Digital
Proceedings of the MediaEval 2013 Multimedia Benchmark Workshop , 1/2013
This paper describes the work done by the TOSCA-MP team for the linking subtask. We submitted three sets of runs: text-only with fixed segments, text-only aligned with shot boundaries, and text and visual with fixed segments. Each of these sets consists of six runs, using combinations of three different types of text resources and for each using only the anchor segment or anchor plus context as input. The results show significant improvements by taking the context of the anchor into account, and smaller improvements when additionally using visual features.