Abstract
Multimodal large language models (MLLMs) have demonstrated strong performance across diverse multimodal tasks, achieving promising outcomes. However, their application to emotion recognition in natural images remains underexplored. MLLMs struggle to handle ambiguous emotional expressions and implicit affective cues, whose capability is crucial for affective understanding but largely overlooked. To address these challenges, we propose MERMAID, a novel multi-agent framework that integrates a multi-perspective self-reflection module, an emotion-guided visual augmentation module, and a cross-modal verification module. These components enable agents to interact across modalities and reinforce subtle emotional semantics, thereby enhancing emotion recognition and supporting autonomous performance. Extensive experiments show that MERMAID outperforms existing methods, achieving absolute accuracy gains of 8.70%–27.90% across diverse benchmarks and exhibiting greater robustness in emotionally diverse scenarios.
Poster
BibTeX
@inproceedings{yang-etal-2025-mermaid,
title = "{MERMAID}: Multi-perspective Self-reflective Agents with Generative Augmentation for Emotion Recognition",
author = "Yang, Zhongyu and
Song, Junhao and
Song, Siyang and
Pang, Wei and
Yuan, Yingfang",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1252/",
doi = "10.18653/v1/2025.emnlp-main.1252",
pages = "24650--24666",
ISBN = "979-8-89176-332-6"}
}