MS${}^2$L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition

Abstract

In this paper, we address self-supervised representation learning from human skeletons for action recognition. Previous methods, which usually learn feature presentations from a single reconstruction task, may come across the overfitting problem, and the features are not generalizable for action recognition. Instead, we propose to integrate multiple tasks to learn more general representations in a self-supervised manner. To realize this goal, we integrate motion prediction, jigsaw puzzle recognition, and contrastive learning to learn skeleton features from different aspects. Skeleton dynamics can be modeled through motion prediction by predicting the future sequence. And temporal patterns, which are critical for action recognition, are learned through solving jigsaw puzzles. We further regularize the feature space by contrastive learning. Besides, we explore different training strategies to utilize the knowledge from self-supervised tasks for action recognition. We evaluate our multi-task self-supervised learning approach with action classifiers trained under different configurations, including unsupervised, semi-supervised and fully-supervised settings. Our experiments on the NW-UCLA, NTU RGB+D, and PKUMMD datasets show remarkable performance for action recognition, demonstrating the superiority of our method in learning more discriminative and general features. Our project website is available at https://langlandslin.github.io/projects/MSL/.

arXiv commentAccepted by ACMMM 2020

References in corpus (1)

• A New Representation of Skeleton Sequences for 3D Action Recognition

Cited by in corpus (8)

• Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences
• Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization
• Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition
• Text-to-Motion Retrieval: Towards Joint Understanding of Human Motion Data and Natural Language
• Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis
• Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition
• Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
• WildGait: Learning Gait Representations from Raw Surveillance Streams