Graph Contrastive Learning for Skeleton-based Action Recognition

01/26/2023
by   Xiaohu Huang, et al.
0

In the field of skeleton-based action recognition, current top-performing graph convolutional networks (GCNs) exploit intra-sequence context to construct adaptive graphs for feature aggregation. However, we argue that such context is still local since the rich cross-sequence relations have not been explicitly investigated. In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (SkeletonGCL) to explore the global context across all sequences. In specific, SkeletonGCL associates graph learning across sequences by enforcing graphs to be class-discriminative, i.e., intra-class compact and inter-class dispersed, which improves the GCN capacity to distinguish various action patterns. Besides, two memory banks are designed to enrich cross-sequence context from two complementary levels, i.e., instance and semantic levels, enabling graph contrastive learning in multiple context scales. Consequently, SkeletonGCL establishes a new training paradigm, and it can be seamlessly incorporated into current GCNs. Without loss of generality, we combine SkeletonGCL with three GCNs (2S-ACGN, CTR-GCN, and InfoGCN), and achieve consistent improvements on NTU60, NTU120, and NW-UCLA benchmarks. The source code will be available at <https://github.com/OliverHxh/SkeletonGCL>.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/14/2021

REGINA - Reasoning Graph Convolutional Networks in Human Action Recognition

It is known that the kinematics of the human body skeleton reveals valua...
research
11/13/2021

A Central Difference Graph Convolutional Operator for Skeleton-Based Action Recognition

This paper proposes a new graph convolutional operator called central di...
research
06/30/2022

Skeleton-based Action Recognition via Adaptive Cross-Form Learning

Skeleton-based action recognition aims to project skeleton sequences to ...
research
04/29/2021

3D Human Action Representation Learning via Cross-View Consistency Pursuit

In this work, we propose a Cross-view Contrastive Learning framework for...
research
05/19/2022

PYSKL: Towards Good Practices for Skeleton Action Recognition

We present PYSKL: an open-source toolbox for skeleton-based action recog...
research
06/29/2021

Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition

One essential problem in skeleton-based action recognition is how to ext...
research
08/01/2020

Augmented Skeleton Based Contrastive Action Learning with Momentum LSTM for Unsupervised Action Recognition

Action recognition via 3D skeleton data is an emerging important topic i...

Please sign up or login with your details

Forgot password? Click here to reset