Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition

TL;DR

This paper introduces PSP Learning, a novel framework that leverages multi-level attention and contrastive learning to improve semi-supervised skeleton-based action recognition by capturing coarse-to-fine semantic features.

Contribution

It proposes a Pyramid Polymerizing Attention mechanism and a Coarse-to-fine Contrastive Loss to jointly learn multi-granularity action representations, enhancing semi-supervised learning performance.

Findings

Achieves competitive results on NTU RGB+D and UCLA datasets.

Effectively captures semantic information at body, part, and joint levels.

Demonstrates the effectiveness of coarse-to-fine contrastive learning.

Abstract

Most semi-supervised skeleton-based action recognition approaches aim to learn the skeleton action representations only at the joint level, but neglect the crucial motion characteristics at the coarser-grained body (e.g., limb, trunk) level that provide rich additional semantic information, though the number of labeled data is limited. In this work, we propose a novel Pyramid Self-attention Polymerization Learning (dubbed as PSP Learning) framework to jointly learn body-level, part-level, and joint-level action representations of joint and motion data containing abundant and complementary semantic information via contrastive learning covering coarse-to-fine granularity. Specifically, to complement semantic information from coarse to fine granularity in skeleton actions, we design a new Pyramid Polymerizing Attention (PPA) mechanism that firstly calculates the body-level attention map, part-level attention map, and joint-level attention map, as well as polymerizes these attention maps in a level-by-level way (i.e., from body level to part level, and further to joint level). Moreover, we present a new Coarse-to-fine Contrastive Loss (CCL) including body-level contrast loss, part-level contrast loss, and joint-level contrast loss to jointly measure the similarity between the body/part/joint-level contrasting features of joint and motion data. Finally, extensive experiments are conducted on the NTU RGB+D and North-Western UCLA datasets to demonstrate the competitive performance of the proposed PSP Learning in the semi-supervised skeleton-based action recognition task. The source codes of PSP Learning are publicly available at https://github.com/1xbq1/PSP-Learning.