MER 2026: From Discriminative Emotion Recognition to Generative Emotion Understanding

TL;DR

MER2026 is a challenge series advancing from basic emotion recognition to complex, multimodal, and generative emotion understanding, emphasizing interaction, fine-grained analysis, preferences, and physiological signals.

Contribution

It introduces four new tracks focusing on dyadic interactions, fine-grained recognition, preference prediction, and physiological signals, expanding the scope of emotion understanding research.

Findings

Introduced four new challenge tracks for emotion understanding.

Expanded from basic recognition to multimodal and generative approaches.

Provided datasets and baselines for future research.

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.