Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network
作者：
Highlights：
• We propose a hierarchical spatial reasoning network for each skeleton frame, which can effectively capture the body-level structural information between each part and the intra spatial relationships of joints in each part with a hierarchical residual graph neural network.
• We propose a temporal stack learning network to model the detailed temporal dynamics of skeleton sequences by a composition of multiple skip-clip LSTMs.
• We perform extensive experiments on five challenging benchmarks to verify the effectiveness of each component of our model. The comparison results illustrate that our approach significantly boosts the performances for skeleton-based action recognition.
摘要
•We propose a hierarchical spatial reasoning network for each skeleton frame, which can effectively capture the body-level structural information between each part and the intra spatial relationships of joints in each part with a hierarchical residual graph neural network.•We propose a temporal stack learning network to model the detailed temporal dynamics of skeleton sequences by a composition of multiple skip-clip LSTMs.•We perform extensive experiments on five challenging benchmarks to verify the effectiveness of each component of our model. The comparison results illustrate that our approach significantly boosts the performances for skeleton-based action recognition.
论文关键词：Skeleton-based action recognition,Hierarchical spatial reasoning,Temporal stack learning,Clip-based incremental loss
论文评审过程：Received 5 December 2019, Revised 10 June 2020, Accepted 17 June 2020, Available online 19 June 2020, Version of Record 23 July 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107511
