Motion Matters: Motion-guided Modulation Network for Skeleton-based Micro-Action Recognition

TL;DR

This paper introduces a Motion-guided Modulation Network (MMN) that effectively captures subtle motion cues in skeleton-based micro-action recognition, significantly improving accuracy over existing methods.

Contribution

The paper proposes a novel MMN with MSM and MTM modules that explicitly model subtle motion cues at skeletal and frame levels, advancing micro-action recognition.

Findings

Achieves state-of-the-art results on Micro-Action 52 dataset

Demonstrates effectiveness of motion-guided modulation modules

Validates approach on iMiGUE dataset

Abstract

Micro-Actions (MAs) are an important form of non-verbal communication in social interactions, with potential applications in human emotional analysis. However, existing methods in Micro-Action Recognition often overlook the inherent subtle changes in MAs, which limits the accuracy of distinguishing MAs with subtle changes. To address this issue, we present a novel Motion-guided Modulation Network (MMN) that implicitly captures and modulates subtle motion cues to enhance spatial-temporal representation learning. Specifically, we introduce a Motion-guided Skeletal Modulation module (MSM) to inject motion cues at the skeletal level, acting as a control signal to guide spatial representation modeling. In parallel, we design a Motion-guided Temporal Modulation module (MTM) to incorporate motion information at the frame level, facilitating the modeling of holistic motion patterns in micro-actions. Finally, we propose a motion consistency learning strategy to aggregate the motion cues from multi-scale features for micro-action classification. Experimental results on the Micro-Action 52 and iMiGUE datasets demonstrate that MMN achieves state-of-the-art performance in skeleton-based micro-action recognition, underscoring the importance of explicitly modeling subtle motion cues. The code will be available at https://github.com/momiji-bit/MMN.