... 10 times for each task. The re-sults reported for each task is obtained by averaging the results of the 10 trials. Note that for each trial, each feature set is trained and tested on the sametraining/test ... 10verbs. We therefore reduce the number of trainingverbs to 9 for each class. For each n = 2, 5, 10, 20,30, 40, 48, we will perform certain number of n-wayclassification tasks. For each n-way ... from each class as training data,and repeat this process 10 times. The accuracy for each n-way task is then computed by averaging the results from these 10 trials. The accuracy reported for the...