This paper presents a method for movie genre categorization of movie trailers, based on scene categorization. We view our approach as a step forward from using only low-level visual feature cues, towards the eventual goal of high-level semantic understanding of feature films. Our approach decomposes each trailer into a collection of keyframes through shot boundary analysis. From these keyframes, we use state-ofthe-art scene detectors and descriptors to extract features, which are then used for shot categorization via unsupervised learning. This allows us to represent trailers using a bag-of-visual-words (bovw) model with shot classes as vocabularies. We approach the genre classification task by mapping bovw temporally structured trailer features to four high-level movie genres: action, comedy, drama or horror films. We have conducted experiments on 1239 annotated trailers. Our experimental results demonstrate that exploiting scene structures improves film genre classification compared to using only low-level visual features.