3D Skeleton-based human action recognition has attracted increasing attention in recent years. Most of the existing work focuses on supervised learning which requires a large number of labeled action sequences that are often expensive and time-consuming to annotate. In this paper, we address self-supervised 3D action representation learning for skeleton-based action recognition. We investigate self-supervised representation learning and design a novel skeleton cloud colorization technique that is capable of learning spatial and temporal skeleton representations from unlabeled skeleton sequence data. We represent a skeleton action sequence as a 3D skeleton cloud and colorize each point in the cloud according to its temporal and spatial orders in the original (unannotated) skeleton sequence. Leveraging the colorized skeleton point cloud, we design an auto-encoder framework that can learn spatial-temporal features from the artificial color labels of skeleton joints effectively. Specifically, we design a two-steam pretraining network that leverages fine-grained and coarse-grained colorization to learn multi-scale spatial-temporal features. In addition, we design a Masked Skeleton Cloud Repainting task that can pretrain the designed auto-encoder framework to learn informative representations. We evaluate our skeleton cloud colorization approach with linear classifiers trained under different configurations, including unsupervised, semi-supervised, fully-supervised, and transfer learning settings. Extensive experiments on NTU RGB+D, NTU RGB+D 120, PKU-MMD, NW-UCLA, and UWA3D datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins and achieves competitive performance in supervised 3D action recognition as well.

翻译：三维基于骨骼的人体动作识别近年来受到越来越多的关注。现有工作大多侧重于监督学习，这需要大量标注的动作序列，而标注过程往往昂贵且耗时。本文针对基于骨骼的动作识别，研究自监督三维动作表征学习。我们探索自监督表征学习，并设计了一种新颖的骨骼云着色技术，能够从未标注的骨骼序列数据中学习空间和时间骨骼表征。我们将骨骼动作序列表示为三维骨骼云，并根据其在原始（未标注）骨骼序列中的时间和空间顺序为云中的每个点着色。利用着色的骨骼点云，我们设计了一种自编码器框架，能够有效从骨骼关节的人工颜色标签中学习时空特征。具体而言，我们设计了一种双流预训练网络，利用细粒度和粗粒度着色学习多尺度时空特征。此外，我们设计了一种掩码骨骼云重绘任务，可预训练所设计的自编码器框架以学习信息丰富的表征。我们在不同配置下训练线性分类器，包括无监督、半监督、全监督和迁移学习设置，评估了我们的骨骼云着色方法。在NTU RGB+D、NTU RGB+D 120、PKU-MMD、NW-UCLA和UWA3D数据集上的大量实验表明，所提方法在无监督和半监督三维动作识别上大幅超越现有方法，并在监督三维动作识别上也取得了具有竞争力的性能。