mlsanityData to 14 Oct 2026

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

arXiv 2604.05900 ↗First posted 7 Apr 2026cs.CVcited by 3

On the map: Multimodal LLMs / vision-language models → Multimodal emotion understanding

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.

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.

Builds on

20 of 43 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025EEmo-Bench: A Benchmark for Multi-modal Large Language Models on Image Evoked Emotion Assessment23 Apr
  2. 2025Evaluating Vision-Language Models for Emotion Recognition8 Feb

Other references · 18

  1. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  2. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  3. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  5. 2023MMBench: Is Your Multi-modal Model an All-around Player?cited by 2,141
  6. 2024Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scalingcited by 1,599
  7. 2022A-OKVQA: A Benchmark for Visual Question Answering using World Knowledgecited by 710
  8. 2024MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmarkcited by 512
  9. 2020Evaluation of Text Generation: A Surveycited by 277
  10. 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoderscited by 218
  11. 2022Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Datasetcited by 100
  12. 2023EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributescited by 82
6 more
  1. 2020Context Based Emotion Recognition using EMOTIC Datasetcited by 73
  2. 2016Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmarkcited by 71
  3. 2024Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Modelscited by 57
  4. 2023What Makes for Good Visual Tokenizers for Large Language Models?cited by 42
  5. 2025Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theorycited by 10
  6. 2024MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Imagecited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026E3mo-Bench: A Scalable Benchmark for Multimodal Evoked and Expressed Emotion Understanding via Bayesian Pairwise Alignmentcited by 1
  2. 2026MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Educationcited by 0
  3. 2026EmoGenie: Benchmarking and Evaluating Expressed and Evoked Emotion in T2I Generation with MLLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MVEI & EmObserver: Empowering MLLM-Oriented Visual Emotional Intelligence via Emotion Statement Judgement
  2. 2026Visual Affect Analysis: Predicting Emotions of Image Viewers with Vision-Language Models
  3. 2025Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach
  4. 2025EmoVLM-KD: Fusing Distilled Expertise with Vision-Language Models for Visual Emotion Analysis
  5. 2024Training A Small Emotional Vision Language Model for Visual Art Comprehension
  6. 2025MMAFFBen: A Multilingual and Multimodal Affective Analysis Benchmark for Evaluating LLMs and VLMs
  7. 2025EmoVerse: A MLLMs-Driven Emotion Representation Dataset for Interpretable Visual Emotion Analysis
  8. 2026Decoding Affective Nuances: Enhancing MLLMs via Hierarchical Emotion Reasoning and Contrastive Discriminative Pruning