Abstract

In view of the dependence of existing 3D action prediction research on labels, we propose a graph convolutional recurrent 3D action prediction method based on state discrimination and spatio-temporal self-supervised contrast learning. In the state discrimination task, cross-sample sampling and relative action completeness perception are used to train the model for generalized state information learning across instances and classes. In the spatio-temporal contrast task, spatio-temporal consistency information is introduced into the feature representation to enrich action semantics in features. Additionally, in order to fully extract spatio-temporal information in 3D action sequences, a spatio-temporal feature extraction network (STFEN) based on graph convolution recurrent network is designed. The experimental results on public datasets demonstrate the efficiency of the proposed methods.

Keywords

MSC

68T01

Cite this article

@article{cai-7071,
  author  = {Peng Liu and Yifan Wang and Qicong Wang and Chong Zhao and Yan Chen and Man Qi},
  title   = {Self-Supervised Learning for 3D Action Prediction with Graph Convolutional Recurrent Network},
  journal = {Computing and Informatics},
  volume  = {44},
  number  = {3},
  pages   = {549--579},
  year    = {2025},
  issn    = {1335-9150},
  doi     = {10.31577/cai_2025_3_549}
}
Download .bib