Artwork Interpretation with Vision Language Models: A Case Study on Emotions and Emotion Symbols

• URL: http://arxiv.org/abs/2511.22929v1
• Date: Fri, 28 Nov 2025 07:04:09 GMT
• Title: Artwork Interpretation with Vision Language Models: A Case Study on Emotions and Emotion Symbols
• Authors: Sebastian Padó, Kerstin Thomas,
• Abstract summary: We investigate which aspects of emotional expression can be detected by current vision language models (VLMs)<n>We find that the VLMs recognize the content of the images surprisingly well and often also which emotions they depict and how they are expressed.<n>The models perform best for concrete images but fail for highly abstract or highly symbolic images.
• Score: 6.1335559884409685
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Emotions are a fundamental aspect of artistic expression. Due to their abstract nature, there is a broad spectrum of emotion realization in artworks. These are subject to historical change and their analysis requires expertise in art history. In this article, we investigate which aspects of emotional expression can be detected by current (2025) vision language models (VLMs). We present a case study of three VLMs (Llava-Llama and two Qwen models) in which we ask these models four sets of questions of increasing complexity about artworks (general content, emotional content, expression of emotions, and emotion symbols) and carry out a qualitative expert evaluation. We find that the VLMs recognize the content of the images surprisingly well and often also which emotions they depict and how they are expressed. The models perform best for concrete images but fail for highly abstract or highly symbolic images. Reliable recognition of symbols remains fundamentally difficult. Furthermore, the models continue to exhibit the well-known LLM weakness of providing inconsistent answers to related questions.

Related papers

• EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis [61.87711517626139]
  EmoVerse is a large-scale open-source dataset that enables interpretable visual emotion analysis.<n>With over 219k images, the dataset further includes dual annotations in Categorical Emotion States (CES) and Dimensional Emotion Space (DES)
  arXiv  Detail & Related papers  (2025-11-16T11:16:50Z)
• Anatomy of a Feeling: Narrating Embodied Emotions via Large Vision-Language Models [1.8349570933241344]
  We propose a framework to generate Embodied LVLM Emotion Narratives (ELENA)<n>These are well-defined, multi-layered text outputs that focus on the salient body parts involved in emotional reactions.<n>We observe that our employed framework can effectively recognize embodied emotions in face-masked images, outperforming baselines without any fine-tuning.
  arXiv  Detail & Related papers  (2025-09-23T21:34:57Z)
• KEVER^2: Knowledge-Enhanced Visual Emotion Reasoning and Retrieval [35.77379981826482]
  We propose textbfK-EVERtextsuperscript2, a knowledge-enhanced framework for emotion reasoning and retrieval.<n>Our approach introduces a semantically structured formulation of visual emotion cues and integrates external affective knowledge through multimodal alignment.<n>We validate our framework on three representative benchmarks, Emotion6, EmoSet, and M-Disaster, covering social media imagery, human-centric scenes, and disaster contexts.
  arXiv  Detail & Related papers  (2025-05-30T08:33:32Z)
• EmoSEM: Segment and Explain Emotion Stimuli in Visual Art [25.539022846134543]
  Given an art image, the model pinpoints pixel regions that trigger a specific human emotion, and generates linguistic explanations for it.<n>This paper proposes the Emotion stimuli and Explanation Model (EmoSEM) model to endow the segmentation framework with emotion comprehension capability.<n>Our method realizes end-to-end modeling from low-level pixel features to high-level emotion interpretation, delivering the first interpretable fine-grained framework for visual emotion analysis.
  arXiv  Detail & Related papers  (2025-04-20T15:40:00Z)
• MEMO-Bench: A Multiple Benchmark for Text-to-Image and Multimodal Large Language Models on Human Emotion Analysis [53.012111671763776]
  This study introduces MEMO-Bench, a comprehensive benchmark consisting of 7,145 portraits, each depicting one of six different emotions. Results demonstrate that existing T2I models are more effective at generating positive emotions than negative ones. Although MLLMs show a certain degree of effectiveness in distinguishing and recognizing human emotions, they fall short of human-level accuracy.
  arXiv  Detail & Related papers  (2024-11-18T02:09:48Z)
• Have Large Vision-Language Models Mastered Art History? [3.790400719319821]
  We test whether Vision-Language Models (VLMs) can classify the style, author and creation date of paintings.<n>Art historians have long studied the unique aspects of artworks, with style prediction being a crucial component of their discipline.
  arXiv  Detail & Related papers  (2024-09-05T13:33:57Z)
• Impressions: Understanding Visual Semiotics and Aesthetic Impact [66.40617566253404]
  We present Impressions, a novel dataset through which to investigate the semiotics of images. We show that existing multimodal image captioning and conditional generation models struggle to simulate plausible human responses to images. This dataset significantly improves their ability to model impressions and aesthetic evaluations of images through fine-tuning and few-shot adaptation.
  arXiv  Detail & Related papers  (2023-10-27T04:30:18Z)
• Affective Image Content Analysis: Two Decades Review and New Perspectives [132.889649256384]
  We will comprehensively review the development of affective image content analysis (AICA) in the recent two decades. We will focus on the state-of-the-art methods with respect to three main challenges -- the affective gap, perception subjectivity, and label noise and absence. We discuss some challenges and promising research directions in the future, such as image content and context understanding, group emotion clustering, and viewer-image interaction.
  arXiv  Detail & Related papers  (2021-06-30T15:20:56Z)
• ArtEmis: Affective Language for Visual Art [46.643106054408285]
  We focus on the affective experience triggered by visual artworks. We ask the annotators to indicate the dominant emotion they feel for a given image. This leads to a rich set of signals for both the objective content and the affective impact of an image.
  arXiv  Detail & Related papers  (2021-01-19T01:03:40Z)
• Facial Expression Editing with Continuous Emotion Labels [76.36392210528105]
  Deep generative models have achieved impressive results in the field of automated facial expression editing. We propose a model that can be used to manipulate facial expressions in facial images according to continuous two-dimensional emotion labels.
  arXiv  Detail & Related papers  (2020-06-22T13:03:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.