• Home
  • Publications
  • Bootstrapped Representation Learning for Skeleton-Based Action Recognition

Research Area

Author

  • Olivier Moliner, Sangxia Huang, Kalle Åström*
  • * External authors

Company

  • Sony Europe B.V.

Venue

  • CVPR

Date

  • 2022

Share

Bootstrapped Representation Learning for Skeleton-Based Action Recognition

View Publication

Abstract

In this work, we study self-supervised representation learning for 3D skeleton-based action recognition. We extend Bootstrap Your Own Latent (BYOL) for representation learning on skeleton sequence data and propose a new data augmentation strategy including two asymmetric transformation pipelines. We also introduce a multi-viewpoint sampling method that leverages multiple viewing angles of the same action captured by different cameras. In the semi-supervised setting, we show that the performance can be further improved by knowledge distillation from wider networks, leveraging once more the unlabeled samples. We conduct extensive experiments on the NTU-60 and NTU-120 datasets to demonstrate the performance of our proposed method. Our method consistently outperforms the current state of the art on both linear evaluation and semi-supervised benchmarks.

CVPR L3D-IVU : Workshop on Learning with Limited Labelled Data for Image and Video Understanding

Share