Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-Based Action Recognition

TL;DR

This paper introduces ActCLR, a self-supervised learning method that adaptively models motion and static parts of skeleton data for improved unsupervised action recognition.

Contribution

It proposes an actionlet-dependent contrastive learning framework that adaptively transforms and pools features based on motion regions, enhancing recognition accuracy.

Findings

Achieves state-of-the-art results on NTU RGB+D and PKUMMD datasets.

Effectively decomposes motion and static regions for better feature learning.

Demonstrates significant improvements over existing self-supervised methods.

Abstract

The self-supervised pretraining paradigm has achieved great success in skeleton-based action recognition. However, these methods treat the motion and static parts equally, and lack an adaptive design for different parts, which has a negative impact on the accuracy of action recognition. To realize the adaptive action modeling of both parts, we propose an Actionlet-Dependent Contrastive Learning method (ActCLR). The actionlet, defined as the discriminative subset of the human skeleton, effectively decomposes motion regions for better action modeling. In detail, by contrasting with the static anchor without motion, we extract the motion region of the skeleton data, which serves as the actionlet, in an unsupervised manner. Then, centering on actionlet, a motion-adaptive data transformation method is built. Different data transformations are applied to actionlet and non-actionlet regions to introduce more diversity while maintaining their own characteristics. Meanwhile, we propose a semantic-aware feature pooling method to build feature representations among motion and static regions in a distinguished manner. Extensive experiments on NTU RGB+D and PKUMMD show that the proposed method achieves remarkable action recognition performance. More visualization and quantitative experiments demonstrate the effectiveness of our method. Our project website is available at https://langlandslin.github.io/projects/ActCLR/