ProFocus: Interpreting Affective Experience in Artistic Images with Progressive Visual Focusing

2026-08-14

AI Summary

This study addresses the challenges of capturing emotional cues and ensuring faithful explanations in art image analysis by proposing a Progressive Visual Focusing framework. Mimicking hierarchical human aesthetic cognition, the method leverages Multimodal Large Language Models to construct layered semantic priors and employs a progressive prompt fusion mechanism to guide visual feature learning, thereby achieving precise cross-modal emotion alignment. Evaluated on the ArtEmis dataset, the proposed framework significantly outperforms state-of-the-art methods in both emotion recognition and explainable generation tasks. These results demonstrate its effectiveness in enhancing the depth and trustworthiness of artistic content understanding, offering a robust solution for aligning computational models with nuanced human aesthetic perception.

Abstract

Interpreting the emotional responses triggered by images is central to achieving emotional intelligence. Compared with natural images, visual art is intentionally created to elicit emotional responses from its viewers through abstract concepts and visual metaphors, making affective interpretation particularly challenging. However, most existing methods rely on general-purpose visual embeddings (e.g., CLIP), failing to capture the nuanced cues underlying artistic emotion. To address this gap, we propose \textbf{ProFocus}, a novel framework that models affective experience in artistic images via progressive visual focusing. The key idea is to model visual representation learning inspired by a hierarchical cognitive theory of human aesthetic appreciation. Technically, ProFocus contains two core components: a Hierarchical Art Critic (HAC) and a Progressive Hint Fusion (PHF) module. HAC leverages multimodal large language models to generate structured linguistic priors at three cognitive levels--atmospheric style, narrative subjects, and concrete details--thereby translating artistic perception into coherent semantic guidance. Building upon these priors, PHF departs from conventional cross-modal fusion by sequentially injecting the hierarchical hints into visual features, enabling a progressive focusing process that mirrors human perception. This design allows the model to capture subtle affective cues and produce more faithful explanations. Extensive experiments on the ArtEmis v1.0 and v2.0 datasets demonstrate that ProFocus consistently outperforms state-of-the-art methods in both emotion recognition and affective explanation. Project page: https://github.com/Zhang-Zhiyan/ProFocus.

Problem

• Affective Computing
• Artistic Image Interpretation
• Emotion Recognition
• Visual Art

Innovation

• Progressive Visual Focusing
• Hierarchical Art Critic
• Progressive Hint Fusion
• Affective Experience Modeling
• Multimodal Large Language Models