Towards Fine-Grained Emotion Understanding via Skeleton-Based Micro-Gesture Recognition

TL;DR

This paper introduces a skeleton-based micro-gesture recognition method for emotion understanding, enhancing a baseline with topology-aware representations, improved temporal modeling, and semantic embeddings, achieving 67.01% accuracy and third place in the challenge.

Contribution

The paper proposes three key enhancements to skeleton-based micro-gesture recognition, improving fine-grained motion modeling and generalization for emotion understanding.

Findings

Achieved 67.01% Top-1 accuracy on iMiGUE dataset.

Ranked third in the IJCAI 2025 MiGA Challenge.

Demonstrated effectiveness of topology-aware skeleton representation.

Abstract

We present our solution to the MiGA Challenge at IJCAI 2025, which aims to recognize micro-gestures (MGs) from skeleton sequences for the purpose of hidden emotion understanding. MGs are characterized by their subtlety, short duration, and low motion amplitude, making them particularly challenging to model and classify. We adopt PoseC3D as the baseline framework and introduce three key enhancements: (1) a topology-aware skeleton representation specifically designed for the iMiGUE dataset to better capture fine-grained motion patterns; (2) an improved temporal processing strategy that facilitates smoother and more temporally consistent motion modeling; and (3) the incorporation of semantic label embeddings as auxiliary supervision to improve the model generalization. Our method achieves a Top-1 accuracy of 67.01\% on the iMiGUE test set. As a result of these contributions, our approach ranks third on the official MiGA Challenge leaderboard. The source code is available at \href{https://github.com/EGO-False-Sleep/Miga25_track1}{https://github.com/EGO-False-Sleep/Miga25\_track1}.