Learning visual models of semantic concepts

Statistical machine learning provides a computational framework for mapping low level media features to high level semantics concepts. In this paper we expose the challenges that these techniques face. Using support vector machine (SVM) classification we build models for 34 semantic concepts for the TREC 2002 benchmark corpus. We study the effect of number of examples available for training with respect to their impact on detection. We also examine low level feature fusion as well as parameter sensitivity with SVM classifiers.