Yang, Siyuan and Liu, Jun and Lu, Shijian and Er, Meng Hwa and Kot, Alex C. (2022) Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning. In: Proceedings - 2021 IEEE/CVF International Conference on Computer Vision, ICCV 2021 :. Proceedings of the IEEE International Conference on Computer Vision . Institute of Electrical and Electronics Engineers Inc., CAN, pp. 13403-13413. ISBN 9781665428132
Full text not available from this repository.Abstract
Skeleton-based human action recognition has attracted increasing attention in recent years. However, most of the existing works focus on supervised learning which requiring a large number of annotated action sequences that are often expensive to collect. We investigate unsupervised representation learning for skeleton action recognition, and design a novel skeleton cloud colorization technique that is capable of learning skeleton representations from unlabeled skeleton sequence data. Specifically, 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. We evaluate our skeleton cloud colorization approach with action classifiers trained under different configurations, including unsupervised, semi-supervised and fully-supervised settings. Extensive experiments on NTU RGB+D and NW-UCLA datasets show that the proposed method outperforms existing unsupervised and semi-supervised 3D action recognition methods by large margins, and it achieves competitive performance in supervised 3D action recognition as well.