Comparing Neural and Attractiveness-based Visual Features for Artwork Recommendation
This work addresses the problem of improving artwork recommendation for online art stores by comparing visual feature methods, but it is incremental as it builds on prior research without introducing a new paradigm.
The study compared deep neural network (DNN) features and explicit visual features (EVF) based on attractiveness for recommending physical artworks, finding that DNN features outperformed EVF and that certain EVF features like brightness were more effective, with evidence suggesting DNN neurons partially encode such visual attributes.
Advances in image processing and computer vision in the latest years have brought about the use of visual features in artwork recommendation. Recent works have shown that visual features obtained from pre-trained deep neural networks (DNNs) perform very well for recommending digital art. Other recent works have shown that explicit visual features (EVF) based on attractiveness can perform well in preference prediction tasks, but no previous work has compared DNN features versus specific attractiveness-based visual features (e.g. brightness, texture) in terms of recommendation performance. In this work, we study and compare the performance of DNN and EVF features for the purpose of physical artwork recommendation using transactional data from UGallery, an online store of physical paintings. In addition, we perform an exploratory analysis to understand if DNN embedded features have some relation with certain EVF. Our results show that DNN features outperform EVF, that certain EVF features are more suited for physical artwork recommendation and, finally, we show evidence that certain neurons in the DNN might be partially encoding visual features such as brightness, providing an opportunity for explaining recommendations based on visual neural models.