← Back to all news
arXiv AI By Ngoc-Duy Mai, Ha-Thanh Nguyen, Hideaki Takeda

Beyond Vision-Language Models: Visual-Semantic Affect Graphs for Emotion Recognition in Artworks

Read the original on arXiv AI →

The paper introduces Visual‑Semantic Affect Graphs (VSAG), a graph‑based framework that models artworks using interpretable feature nodes such as color, brushstroke, composition, and visual entities. VSAG learns feature‑emotion associations and optionally incorporates a hierarchical valence‑arousal module to predict dominant emotions. Experiments on EmoArt‑5k show that VSAG, especially its valence‑arousal variant, outperforms direct vision‑language model inference and improves accuracy, macro‑F1, and weighted‑F1 scores, indicating that explicit visual‑semantic structure enhances both prediction and interpretation of artwork emotions.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

Hugging Face Trending Papers
Jul 23

MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement

Affective Image Content Analysis (AICA) aims to recognize and understand emotions elicited by visual content, representing an indispensable step toward Artificial General Intelligence (AGI). However, despite the rapid progress of Multimodal Large Language Models (MLLMs), systematic evaluation of their visual emotional intelligence remains largely absent from recent model releases.

llmsmultimodalbenchmarks
More like this →
arXiv Computer Vision
Sep 30

Decoding Affective Nuances: Enhancing MLLMs via Hierarchical Emotion Reasoning and Contrastive Discriminative Pruning

The paper introduces DAN, a training‑free inference‑time framework that improves affective reasoning in multimodal large language models. It combines a Hierarchical Emotional Reasoning Chain (HERC) to better capture fine‑grained visual cues and a Contrastive Discriminative Visual Pruning (CDVP) module to isolate discriminative tokens for semantically similar emotions. Experiments show significant gains, notably a +10.47% improvement on the WebEmo25 benchmark with Qwen3‑VL‑8B‑Instruct.

By Cheng Ye, Weidong Chen, Zhaobo Qi, Beier Zhu, Zhendong Mao
llmsefficiencymultimodalbenchmarks
More like this →
arXiv Computer Vision
Oct 26

Forging Emotions: a deep learning experiment on emotions and art

The paper "Forging Emotions" investigates how Generative Adversarial Networks (GANs) can be used to generate images that convey or trigger specific emotions. It highlights that current datasets for high‑level concepts like emotions are inadequate and suggests incorporating psychological emotional networks into dataset construction. The study also finds that simple color cues are insufficient for affect generation, advocating for deeper analysis of GAN structure and composition to create genuinely emotive imagery.

By Amalia Foka
diffusionsafety
More like this →