OmniArt: Multi-task Deep Learning for Artistic Data Analysis is a paper about a multi-task deep architecture that learns joint representations of data based on multiple tasks. The motivation behind this work is to determine whether looking at artistic data from multiple aspects is beneficial to deep models like it is for the human professionals and can that information be captured in a learned representation of the data.
In this paper we also introduce a new structured artistic dataset with rich metadata dubbed OmniART which will be publicly released uppon publication.