Graph Convolutional Networks for Temporal Action Localization

Graph Deep Learning


  • Runhao Zeng
  • Wenbing Huang
  • Mingkui Tan
  • Yu Rong
  • Peilin Zhao
  • Junzhou Huang
  • Chuang Gan

Published on


Most state-of-the-art action localization systems process each action proposal individually, without explicitly exploiting their relations during learning. However, the relations between proposals actually play an important role in action localization, since a meaningful action always consists of multiple proposals in a video. In this paper, we propose to exploit the proposal-proposal relations using Graph Convolutional Networks (GCNs). First, we construct an action proposal graph, where each proposal is represented as a node and their relations between two proposals as an edge. Here, we use two types of relations, one for capturing the context information for each proposal and the other one for characterizing the correlations between distinct actions. Then we apply the GCNs over the graph to model the relations among different proposals and learn powerful representations for the action classification and localization. Experimental results show that our approach significantly outperforms the state-of-the-art on THUMOS14 (49.1% versus 42.8%). Moreover, augmentation experiments on ActivityNet also verify the efficacy of modeling action proposal relationships.

Please cite our work using the BibTeX below.

   title={Graph Convolutional Networks for Temporal Action Localization},
   journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
   author={Zeng, Runhao and Huang, Wenbing and Gan, Chuang and Tan, Mingkui and Rong, Yu and Zhao, Peilin and Huang, Junzhou},
Close Modal