Two-stream adaptive-attentional subgraph convolution networks for skeleton-based action recognition

Autor: Fengda Zhao, Fengwei Lou, Xianshan Li, Rong Jing, Dingding Guo, Fengchan Meng
Rok vydání: 2021
Předmět:
Zdroj: Multimedia Tools and Applications. 81:4821-4838
ISSN: 1573-7721
1380-7501
DOI: 10.1007/s11042-021-11026-4
Popis: Recently, skeleton-based action recognition has modeled the human skeleton as a graph convolution network (GCN), and has achieved remarkable results. However, most of the methods convolute directly on the whole graph, neglecting that the human skeleton is made up of multiple body parts, which cannot accomplish the task well. We recognize that the physical property of bones (i.e., length and direction) can provide identifiable information which helps effectively to build the multi-level network structure. As the existing methods treat the channel domain and the spatial domain with equal importance, many computing resources are wasted on neglectable features. In our paper, we modify the Convolution Block Attention Module (CBAM) and apply it to the adaptive network. By capturing the implicit weighted information in the channel domain and spatial domain, the network can focus more attention on the key channels and nodes. A new two-stream adaptive-attentional subgraph convolution network (2s-AASGCN) is proposed to extract features in the spatio-temporal domain. We validate 2s-AASGCN on two skeleton datasets, i.e., NTU-RGB+D60 and NTU-RGB+D120. Our model achieves excellent results on these two datasets.
Databáze: OpenAIRE
Externí odkaz: