Exploiting probabilistic relationships between action concepts for complex event classification

Videos of complex events are difficult to represent solely as bags of low level features. Increasingly, supervised concepts or attributes are being employed as the intermediate representation of such videos. We propose a probabilistic framework that models the conditional relationships between the concepts and events and devise an approximate yet tractable solution to infer the posterior distribution to perform event classification. Using noisy outputs of pre-trained concept detectors, we learn semantic and visual dependencies between event and concept pairs. The co-occurrence between concept pairs is also learned as a marginal over training samples. The proposed method then employs the learned prior, as well as the probabilities of occurrence of specific concepts in a test video to infer the probability of each event using weighted average one-dependence estimation. The evaluation shows that our method improves event classification compared to recent literature on the TRECVID data set.