# AICA-Bench: Holistically Examining the Capabilities of VLMs in Affective Image Content Analysis

arXiv: https://arxiv.org/abs/2604.05900 · HTML: https://mlsanity.com/paper/2604.05900/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal emotion understanding, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 20 of its 43 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Multimodal emotion understanding](https://mlsanity.com/mllm/multimodal-emotion-understanding/)

## Builds on (most cited first, 20 of 20)

- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset](https://mlsanity.com/paper/2205.12522/) (2022)
- [EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes](https://mlsanity.com/paper/2307.07961/) (2023)
- [Context Based Emotion Recognition using EMOTIC Dataset](https://mlsanity.com/paper/2003.13401/) (2020)
- [Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark](https://mlsanity.com/paper/1605.02677/) (2016)
- [Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models](https://mlsanity.com/paper/2402.12058/) (2024)
- [What Makes for Good Visual Tokenizers for Large Language Models?](https://mlsanity.com/paper/2305.12223/) (2023)
- [Evaluating Vision-Language Models for Emotion Recognition](https://mlsanity.com/paper/2502.05660/) (2025)
- [EEmo-Bench: A Benchmark for Multi-modal Large Language Models on Image Evoked Emotion Assessment](https://mlsanity.com/paper/2504.16405/) (2025)
- [Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory](https://mlsanity.com/paper/2505.10981/) (2025)
- [MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image](https://mlsanity.com/paper/2412.00060/) (2024)

## Built on by (most cited first, 3 of 3)

- [E3mo-Bench: A Scalable Benchmark for Multimodal Evoked and Expressed Emotion Understanding via Bayesian Pairwise Alignment](https://mlsanity.com/paper/2608.10796/) (2026)
- [MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education](https://mlsanity.com/paper/2609.19088/) (2026)
- [EmoGenie: Benchmarking and Evaluating Expressed and Evoked Emotion in T2I Generation with MLLMs](https://mlsanity.com/paper/2610.18455/) (2026)

## Abstract (arXiv)

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 gap, we introduce AICA-Bench, a comprehensive benchmark with three core tasks: Emotion Understanding (EU), Emotion Reasoning (ER), and Emotion-Guided Content Generation (EGCG). We evaluate 23 VLMs and identify two major limitations: weak intensity calibration and shallow open-ended descriptions. To address these issues, we propose Grounded Affective Tree (GAT) Prompting, a training-free framework that combines visual scaffolding with hierarchical reasoning. Experiments show that GAT reduces intensity errors and improves descriptive depth, providing a strong baseline for future research on affective multimodal understanding and generation.