For evaluation purposes, three distinct training and test- ing splits were generated from the database. The sets were built to ensure that clips from the same video were not used for both training and testing and that the relative proportions of meta tags such as camera position, video quality, motion, etc. were evenly distributed across the training and testing sets. For each action category in our dataset we selected sets of 70 training and 30 testing clips so that they fulfill the 70/30 balance for each meta tag with the added constraint that clips in the training and testing set could not come from the same video file. To this end,.
