Prompted Contrast with Masked Motion Modeling: Towards Versatile 3D Action Representation Learning

TL;DR

This paper introduces PCM$^{ m 3}$, a novel self-supervised learning framework that effectively combines contrastive learning and masked motion modeling to improve versatile 3D action representation learning, enhancing generalization across multiple tasks.

Contribution

The paper proposes a unified framework that integrates contrastive learning with masked motion modeling using a dual-prompted multi-task pretraining strategy, addressing their previous limitations.

Findings

Outperforms state-of-the-art on five downstream tasks

Demonstrates superior generalization across three large-scale datasets

Effectively reduces training interference between tasks

Abstract

Self-supervised learning has proved effective for skeleton-based human action understanding, which is an important yet challenging topic. Previous works mainly rely on contrastive learning or masked motion modeling paradigm to model the skeleton relations. However, the sequence-level and joint-level representation learning cannot be effectively and simultaneously handled by these methods. As a result, the learned representations fail to generalize to different downstream tasks. Moreover, combining these two paradigms in a naive manner leaves the synergy between them untapped and can lead to interference in training. To address these problems, we propose Prompted Contrast with Masked Motion Modeling, PCM$^{\rm 3}$, for versatile 3D action representation learning. Our method integrates the contrastive learning and masked prediction tasks in a mutually beneficial manner, which substantially boosts the generalization capacity for various downstream tasks. Specifically, masked prediction provides novel training views for contrastive learning, which in turn guides the masked prediction training with high-level semantic information. Moreover, we propose a dual-prompted multi-task pretraining strategy, which further improves model representations by reducing the interference caused by learning the two different pretext tasks. Extensive experiments on five downstream tasks under three large-scale datasets are conducted, demonstrating the superior generalization capacity of PCM$^{\rm 3}$ compared to the state-of-the-art works. Our project is publicly available at: https://jhang2020.github.io/Projects/PCM3/PCM3.html .