Multi-Scale Adaptive Graph Convolutional Network for Skeleton-Based Action Recognition
- Resource Type
- Conference
- Authors
- Fan, Yiqi; Wang, Xiaojuan; Lv, Tianqi; Wu, Lingrui
- Source
- 2020 15th International Conference on Computer Science & Education (ICCSE) Computer Science & Education (ICCSE), 2020 15th International Conference on. :517-522 Aug, 2020
- Subject
- Computing and Processing
Engineering Profession
Robotics and Control Systems
Skeleton
Feature extraction
Adaptive systems
Task analysis
Aggregates
Fuses
Telecommunications
multi-scale
graph convolutional networks
attention mechanism
skeleton-based action recognition
- Language
- ISSN
- 2473-9464
Skeleton-based action recognition is a branch of action recognition which uses dynamic skeletons as input. Recent research based on graph convolutional networks (GCN) has achieved remarkable performance in this area. However, feature extraction and fusion at different physical scales have not been well studied. To solve these issues, we propose a novel MultiScale Adaptive Graph Convolutional Network (MSGCN) which contains a Multi-Scale Graph Convolutional Module and a MultiScale Selective Fusion Module. Extensive experiments on NTU- RGBD dataset demonstrate the effectiveness of our method, our method achieved competitive performance on NTU-RGBD dataset.