Graph Convolutional Hourglass Networks for Skeleton-Based Action Recognition

Yiran Zhu, Xing Xu, Yanli Ji, Fumin Shen, Heng Tao Shen, Huimin LuICME 2021 · OpenReview

Abstract

Graph convolution networks (GCNs) have become the mainstream framework for the skeleton-based action recognition task, since the skeleton representation of human action can be naturally modeled by the graph structure. Generally, most of the existing GCN based models extract and aggregate skeleton features by exploiting single-scale joint information, while neglecting the valuable multi-scale information such as part and body features in the skeleton. To address this issue, we propose a novel Graph Convolutional Hourglass Network (GCHN) model, which is scalable by stacking several basic modules of Graph Convolutional Hourglass Block (GCHB). Each GCHB module consists of the sequential operations of graph convolution, graph pooling and graph unpooling, which can promote the interaction of multi-scale information in the skeleton and effectively improve the recognition performance. Extensive experiments on the challenging NTU-RGB+D and Kinetics-Skeleton datasets demonstrate that the proposed GCHN model achieves state-of-the-art performance.
BibTeX
@inproceedings{zhu2021graph,
  author = {Yiran Zhu and Xing Xu and Yanli Ji and Fumin Shen and Heng Tao Shen and Huimin Lu},
  title = {{Graph Convolutional Hourglass Networks for Skeleton-Based Action Recognition}},
  booktitle = {ICME},
  year = {2021},
  url = {https://openreview.net/forum?id=xtYAiv0fExV},
}

Loading related content...

Figure