Smell and Emotion: Recognising emotions in smell-related artworks

TL;DR

This paper explores the feasibility of recognizing emotions in smell-related artworks, demonstrating technical potential with room for improvement, and employing style transfer and hyperparameter tuning to enhance performance.

Contribution

It introduces a method for emotion recognition in smell-related artworks and applies style transfer and hyperparameter optimization to improve results.

Findings

Emotion recognition is feasible in smell-related artworks.

Style transfer and hyperparameter tuning yield performance improvements.

The field remains open for further enhancements.

Abstract

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.