Automatic evaluation method for rushes summary content
Emilie Dumont, Bernard Mérialdo · 2009
During the last years, the development of rushes video summarization systems has greatly increased thanks to the international evaluation campaign TRECVID. In this paper, we propose an automation of the manual TRECVID evaluation using machine learning techniques. We train an automatic assessor to perform evaluation on summary content and we show a high correlation between the manual evaluation performed in TRECVID 2008 and our automatic assessor.