Abstract
We address the challenging problem of utilizing relatedexemplars for complex event detection while multiple fea-tures are available. Related exemplars share certain posi-tive elements of the event, but have no uniform pattern dueto the huge variance of relevance levels among different re-lated exemplars. None of the existing multiple feature fusion methods can deal with the related exemplars. In thispaper, we propose an algorithm which adaptively utilizesthe related exemplars by cross-feature learning. Ordinal labels are used to represent the multiple relevance levels of the related videos. Label candidates of related exemplars are generated by exploring the possible relevance levels of each related exemplar via a cross-feature voting strategy. Maximum margin criterion is then applied in our framework to discriminate the positive and negative exemplars, as well as the related exemplars from different relevance levels. We test our algorithm using the large scale TRECVID 2011 dataset and it gains promising performance.