Abstract
For people first impressions of someone are of determin-ing importance. They are hard to alter through further in-formation. This begs the question if a computer can reachthe same judgement. Earlier research has already pointedout that age, gender, and average attractiveness can be es-timated with reasonable precision. We improve the state-of-the-art, but also predict based on someone’s knownpreferences how much that particular person is attractedto a novel face. Our computational pipeline comprises aface detector, convolutional neural networks for the extraction of deep features, standard support vector regression for gender, age and facial beauty, and as the main novelties visual regularized collaborative filtering to infer inte person preferences as well as a novel regression technique for handling visual queries without rating history. We validate the method using a very large dataset from a dating site as well as images from celebrities. Our experiments yield convincing results, i.e. we predict 76% of the ratings correctly solely based on an image, and reveal some sociologically relevant conclusions. We also validate our collaborative filtering solution on the standard MovieLens rating dataset, augmented with movie posters, to predict an individuals movie rating. We demonstrate our algorithms on howhot.io which went viral around the Internet with more than 50 million pictures evaluated in the first month.