Smell and Emotion: Recognising emotions in smell-related artworks
This work addresses the gap in emotion recognition for smell-related artworks in digital art history, but it is incremental in nature.
The study tackled the problem of recognizing emotions in smell-related artworks, an underrepresented area in digital art history, and found it technically feasible but with room for improvement, achieving a minor performance boost through style transfer and hyperparameter optimization.
Emotions and smell are underrepresented in digital art history. In this exploratory work, we show that recognising emotions from smell-related artworks is technically feasible but has room for improvement. Using style transfer and hyperparameter optimization we achieve a minor performance boost and open up the field for future extensions.