Exploiting generalized discriminative multiple instance learning for multimedia semantic concept detection

A generalized discriminative multiple instance learning (GDMIL) algorithm is presented to train the classifier in the condition of vague annotation of training samples GDMIL not only inherits the original MIL's capability of automatically weighting the instances in the bag according to their relevance to the concept but also integrates generative models using discriminative training. It is evaluated on the task of multimedia semantic concept detection using the development data set of TRECVID 2005. The experimental results show GDMIL outperforms the baseline systems trained on MIL with diverse density and expectation–maximization diverse density and the system without MIL.