Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network. (November 2020)

• Record Type: Journal Article
• Authors: Si, Chenyang; Jing, Ya; Wang, Wei; Wang, Liang; Tan, Tieniu
• Is Part Of: Pattern recognition. Volume 107(2020:Nov.)
• Publication Date: 2020-11
• Subjects: Skeleton-based action recognition -- Hierarchical spatial reasoning -- Temporal stack learning -- Clip-based incremental loss; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2020.107511
• Languages: English
• ISSNs: 0031-3203

Abstract

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. Abstract: Skeleton-based action recognition aims to recognize human actions by exploring the inherent characteristics from the given skeleton sequences and has attracted far more attention due to its great important potentials in practical applications. Previous methods have illustrated that learning discriminative spatial and temporal features from the skeleton sequences is a crucial factor to recognize human actions. Nevertheless, how to model spatio-temporal evolutions is still a challenging problem. In this work, we propose a novel model with hierarchical spatial reasoning and temporal stack learning network (HSR-TSL) to explore the discriminative spatial and temporal features for human action recognition, which consists of a hierarchical spatial reasoning network (HSRN) and a temporal stack learning network (TSLN). Specifically, the HSRN employs a hierarchical residual graph neural network to capture two-level spatial features: intra spatial information of each part and body-level structural information between each part. The TSLN models the detailed temporal dynamics of skeleton sequences by a composition of multiple skip-clip LSTMs. During training, we develop a clip-based incremental loss to effectively optimize the model. 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.