MER 2026: From Discriminative Emotion Recognition to Generative Emotion Understanding
Zheng Lian, Xiaojiang Peng, Kele Xu, Ziyu Jia, Xinyi Che + 12 more
TLDR
MER2026 expands emotion understanding challenges from discriminative recognition to generative analysis, introducing new tasks and multimodal approaches.
Key contributions
- Shifts from discriminative emotion recognition to generative emotion understanding.
- Introduces four new tracks: dyadic interactions, fine-grained recognition, preference prediction, and physiological signals.
- Leverages MLLMs for more explainable and fine-grained emotion analysis.
- Provides valuable data resources and tasks for the emotion research community.
Why it matters
This paper outlines the MER2026 challenge, pushing emotion AI from simple recognition to complex generative understanding. By introducing new tasks and leveraging MLLMs, it fosters more nuanced, explainable, and context-aware emotion analysis. This advancement is crucial for developing more human-like AI interactions.
Original Abstract
MER2026 marks the fourth edition of the MER series of challenges. The MER series provides valuable data resources to the research community and offers tasks centered on recent research trends, establishing itself as one of the largest challenges in the field. Throughout its history, the focus of MER has shifted from discriminative emotion recognition to generative emotion understanding. Specifically, MER2023 concentrated on discriminative emotion recognition, restricting the emotion recognition scope to fixed basic labels. In MER2024 and MER2025, we transitioned to generative emotion understanding and introduced two new tasks: fine-grained emotion recognition and descriptive emotion analysis, aiming to leverage the extensive vocabulary and multimodal understanding capabilities of Multimodal Large Language Models (MLLMs) to facilitate fine-grained and explainable emotion recognition. Building on this trajectory, MER2026 continues to follow these research trends and contains four tracks: MER-Cross shifts the focus from individual to dyadic interaction scenarios; MER-FG centers on fine-grained emotion recognition; MER-Prefer aims to predict human preferences regarding different emotion descriptions; MER-PS focuses on emotion recognition based on physiological signals. More details regarding the dataset and baselines are available at https://zeroqiaoba.github.io/MER-Challenge.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.