Aesthetic Features for Personalized Photo Recommendation
This addresses the problem of recommending aesthetically pleasing photos to users on photography websites, but it is incremental as it builds on existing collaborative filtering methods.
The paper tackled personalized photo recommendation by proposing aesthetic feature extraction methods based on color space and deep style transfer embeddings, showing that deep style transfer embeddings significantly boost performance on a 500px dataset.
Many photography websites such as Flickr, 500px, Unsplash, and Adobe Behance are used by amateur and professional photography enthusiasts. Unlike content-based image search, such users of photography websites are not just looking for photos with certain content, but more generally for photos with a certain photographic "aesthetic". In this context, we explore personalized photo recommendation and propose two aesthetic feature extraction methods based on (i) color space and (ii) deep style transfer embeddings. Using a dataset from 500px, we evaluate how these features can be best leveraged by collaborative filtering methods and show that (ii) provides a significant boost in photo recommendation performance.