Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition

10 Aug 2021  ·  Tailin Chen, Desen Zhou, Jian Wang, Shidong Wang, Yu Guan, Xuming He, Errui Ding ·

The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion. Existing approaches typically employ a single neural representation for different motion patterns, which has difficulty in capturing fine-grained action classes given limited training data. To address the aforementioned problems, we propose a novel multi-granular spatio-temporal graph network for skeleton-based action classification that jointly models the coarse- and fine-grained skeleton motion patterns. To this end, we develop a dual-head graph network consisting of two interleaved branches, which enables us to extract features at two spatio-temporal resolutions in an effective and efficient manner. Moreover, our network utilises a cross-head communication strategy to mutually enhance the representations of both heads. We conducted extensive experiments on three large-scale datasets, namely NTU RGB+D 60, NTU RGB+D 120, and Kinetics-Skeleton, and achieves the state-of-the-art performance on all the benchmarks, which validates the effectiveness of our method.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Skeleton Based Action Recognition Kinetics-Skeleton dataset DualHead-Net Accuracy 38.4 # 4
Skeleton Based Action Recognition NTU RGB+D DualHead-Net Accuracy (CV) 96.6 # 13
Accuracy (CS) 92.0 # 13
Skeleton Based Action Recognition NTU RGB+D 120 DualHead-Net Accuracy (Cross-Subject) 88.2 # 11
Accuracy (Cross-Setup) 89.3 # 11

Methods


No methods listed for this paper. Add relevant methods here