@inproceedings{she-etal-2026-aica,
    title = "{AICA}-Bench: Holistically Examining the Capabilities of {VLM}s in Affective Image Content Analysis",
    author = "She, Dong  and
      Yao, Xianrong  and
      Chen, Liqun  and
      Yu, Jinghe  and
      Gao, Yang  and
      Jin, Zhanpeng",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.661/",
    pages = "13501--13528",
    ISBN = "979-8-89176-395-1",
    abstract = "Vision-Language Models (VLMs) have demonstrated strong capabilities in perception, yet holistic Affective Image Content Analysis (AICA){---}which integrates perception, reasoning, and generation into a unified framework{---}remains underexplored. To address this, we introduce AICA-Bench, a comprehensive benchmark comprising three core tasks: Emotion Understanding (EU), Reasoning (ER), and Generation (EGCG). We evaluate 23 VLMs, revealing critical gaps: models struggle with intensity calibration and suffer from descriptive shallowness in open-ended tasks. To bridge these gaps, we propose Grounded Affective Tree (GAT) Prompting, a training-free framework that integrates visual scaffolding with hierarchical reasoning. Experiments show that GAT effectively corrects intensity errors and significantly enhances descriptive depth, establishing a robust baseline for future affective multimodal research."
}