# Why Do Vision Language Models Struggle To Recognize Human Emotions?

arXiv: https://arxiv.org/abs/2604.15280 · HTML: https://mlsanity.com/paper/2604.15280/

## Key facts

- Cited by 1 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 54 of its 75 references that are in the map.
- First posted on arXiv 16 Apr 2026.

## Placed in

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

## Builds on (most cited first, 30 of 54)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Deep Long-Tailed Learning: A Survey](https://mlsanity.com/paper/2110.04596/) (2021)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect](https://mlsanity.com/paper/2009.12991/) (2020)
- [VTimeLLM: Empower LLM to Grasp Video Moments](https://mlsanity.com/paper/2311.18445/) (2023)
- [Distribution Alignment: A Unified Framework for Long-tail Visual Recognition](https://mlsanity.com/paper/2103.16370/) (2021)
- [DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wild](https://mlsanity.com/paper/2008.05924/) (2020)
- [Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective](https://mlsanity.com/paper/2002.10826/) (2020)
- [MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2208.00847/) (2022)

## Built on by (most cited first, 1 of 1)

- [Social Intuition vs. Machine Reasoning: Anticipating Human-Robot Interaction from multiple modalities](https://mlsanity.com/paper/2609.07394/) (2026)

## Abstract (arXiv)

Understanding emotions is a fundamental ability for intelligent systems to be able to interact with humans. Vision-language models (VLMs) have made tremendous progress in the last few years for many visual tasks, potentially offering a promising solution for understanding emotions. However, it is surprising that even the most sophisticated contemporary VLMs struggle to recognize human emotions or to outperform even specialized vision-only classifiers. In this paper we ask the question 'Why do VLMs struggle to recognize human emotions?', and observe that the inherently continuous and dynamic task of facial expression recognition (DFER) exposes two critical VLM vulnerabilities. First, emotion datasets are naturally long-tailed, and the web-scale data used to pre-train VLMs exacerbates this head-class bias, causing them to systematically collapse rare, under-represented emotions into common categories. We propose alternative sampling strategies that prevent favoring common concepts. Second, temporal information is critical for understanding emotions. However, VLMs are unable to represent temporal information over dense frame sequences, as they are limited by context size and the number of tokens that can fit in memory, which poses a clear challenge for emotion recognition. We demonstrate that the sparse temporal sampling strategy used in VLMs is inherently misaligned with the fleeting nature of micro-expressions (0.25-0.5 seconds), which are often the most critical affective signal. As a diagnostic probe, we propose a multi-stage context enrichment strategy that utilizes the information from 'in-between' frames by first converting them into natural language summaries. This enriched textual context is provided as input to the VLM alongside sparse keyframes, preventing attentional dilution from excessive visual data while preserving the emotional trajectory.