Predicting Movie Ratings from Audience Behaviors

We propose a method of representing audience behavior through facial and body motions from a single video stream, and use these features to predict the rating for feature-length movies.

We propose a method of representing audience behavior through facial and body motions from a single video stream and use these motions to predict the rating for feature-length movies. This is a very challenging problem as i) the movie viewing environment is dark and contains views of people at different scales and viewpoints; ii) the duration of feature-length movies is long (80-120 mins) so tracking people uninterrupted for this length of time is an unsolved problem; and iii) expressions and motions of audience members are subtle, short and sparse making labeling of activities unreliable. To circumvent these issues, we use an infra-red illuminated test-bed to obtain a visually uniform input. We then utilize motion-history features which capture the subtle movements of a person within a pre-defined volume and then form a group representation of the audience by a histogram of pair-wise correlations over small time windows. Using this group representation, we learn a movie rating classifier from crowd-sourced ratings collected by rottentomatoes.com and show our prediction capability on audiences from 30 movies across 250 subjects (> 50 hours).