Problem
Research questions and friction points this paper is trying to address.
visual emotion analysis
emotion prediction
artworks
dimensional emotion space
museum exhibitions
Dimensional Distribution Emotion State: Leveraging Valence and Arousal as a Common Embedding Space for Visual Emotion Analysis
🤖 AI Summary
This study addresses the high cost, labor intensity, and susceptibility to subjective bias inherent in manual affective annotation of artworks by proposing a novel emotion representation framework termed DDES (Dimensional and Discrete Emotion Space). Integrating the strengths of both discrete categorical and continuous dimensional emotion models, DDES operates within a valence–arousal two-dimensional space and leverages a deep learning architecture trained jointly across multiple datasets. Emotion states are represented as probability distributions to better capture affective uncertainty and nuance. Experimental results demonstrate that DDES not only maintains baseline performance but also significantly enhances emotional expressiveness and cross-dataset generalization, thereby offering an efficient and objective technical foundation for emotion-driven art curation and exhibition design.
📝 Abstract
Museums are important sites for the dissemination of culture and art. They are institutions rooted in history and tradition; their exhibitions are often designed to highlight these aspects. Recently, a new approach is being explored in the field: emotion-based exhibitions. These exhibitions are designed specifically to elicit emotions in the visitors, in order to maximize engagement, and as a way to democratize access to art and attract a wider, more diverse audience. To do so, the emotional content of the artworks must first be extracted, however, manually annotating the artworks by experts is a prohibitively labor-intensive process, and risks introducing the personal bias of curators. To assist the museum curators in their design of these exhibitions, we wish to develop a tool that can predict the emotional response evoked by a work of art. In this article, we leverage a continuous bi-dimensional emotion space to enhance emotion representations and the training process of deep learning models. Drawing inspiration from existing categorical and dimensional emotion representations, we introduce a new representation, Dimensional Distribution Emotion State (DDES), along with a pipeline for multi-dataset training. We show that DDES provides multiple advantages compared to widely used representations while exhibiting similar baseline performance.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Dimensional Distribution Emotion State
Valence-Arousal Space
Visual Emotion Analysis
Multi-dataset Training
Emotion Representation
🔎 Similar Papers
No similar papers found.
