We Like It! Mapping Image Preferences On The Counting Grid

Modeling user preferences in photographic images is often reduced to analyzing intermediate explicit representations (e.g. textual tags) as means of capturing the objective and subjective properties of image perception, trying to distill the essence of what gives pleasure. We propose an alternative approach that bypasses the necessity to build an explicit conceptual coding of image preferences, operating directly on the raw properties of the images, extracted with heterogeneous feature descriptors. This is achieved through the counting grid model, which fuses together content-based and aesthetics themes into a 2D map in an unsupervised way. We show that certain locations in this map correspond to perceptually intuitive image classes, even without relying on tags or other user-defined information. Moreover, we show that users' individual preferences can be represented as distributions over the map, allowing us to evaluate the affinity between different users' appreciations. We experiment on a large Flickr dataset, clustering users by affinity, and validating these clusters by checking users that belong to the same Flickr photo groups.