IRIM at TRECVID 2008: High Level Feature Extraction

The IRIM group is a consortium of French teams working on Multimedia Indexing and Retrieval. This paper describes our participation to the TRECVID 2008 High Level Features detection task. We evaluated several fusion strategies and especially rank fusion. Results show that including as many low-level and intermediate features as possible is the best strategy, that SIFT features are very important, that the way in which the fusion from the various low-level and intermediate features does matter, that the type of mean (arithmetic, geometric and harmonic) does matter but which is better depends upon the fused sources. Our best run has a Mean Inferred Average Precision of 0.0885, which is significantly above TRECVID 2008 HLF detection task median performance.

• Type: Conference
• Year: 2008
• Where: TRECVID
• Authors: Hervé Glotin, Zhongqui Zhao, Stéphane Ayache, Georges Quénot
• Keywords: Detection Task, Features Detection Task, Intermediate Features, Internet Technology, TRECVID 2008