Journal article
Topology-learnable graph convolution for skeleton-based action recognition
Pattern Recognition Letters, Vol.135, pp.286-292
2020
Abstract
Graph convolutional networks (GCNs) generalize convolutional neural networks into irregular graph-like structures. Generally, graph topologies are set by hand and fixed over all layers. Handcrafted connections may not be optimal and cannot fully use the self-learning ability of deep learning. In this work, we explore a topology-learnable graph convolution for skeleton-based action recognition. Specifically, a spatial graph convolution can be decomposed into a feature learning component that evolves the features of each graph vertex, and a graph vertex fusion component in which the latent graph topologies can be learned adaptively. Different initialization strategies for the learnable fusion matrix are evaluated. Experimental results that are based on the spatial-temporal GCNs for skeleton-based action recognition, demonstrate that convolution can work on graphs like on images, even if only a specific fusion matrix initialization that uses adjacency matrices is applied. Moreover, the self-learning process can learn the latent topology of a graph beyond the handcrafted topology, thereby making graph convolution flexible and universal.
Details
- Title
- Topology-learnable graph convolution for skeleton-based action recognition
- Authors/Creators
- G. Zhu (Author/Creator) - Xidian UniversityL. Zhang (Author/Creator) - Xidian UniversityH. Li (Author/Creator) - Xidian UniversityP. Shen (Author/Creator) - Xidian UniversityS.A.A. Shah (Author/Creator) - Murdoch UniversityM. Bennamoun (Author/Creator) - The University of Western Australia
- Publication Details
- Pattern Recognition Letters, Vol.135, pp.286-292
- Publisher
- Elsevier B.V.
- Identifiers
- 991005542958707891
- Copyright
- © 2020 Elsevier B.V.
- Murdoch Affiliation
- Information Technology, Mathematics and Statistics
- Language
- English
- Resource Type
- Journal article
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites
Metrics
49 Record Views
InCites Highlights
These are selected metrics from InCites Benchmarking & Analytics tool, related to this output
- Collaboration types
- Domestic collaboration
- International collaboration
- Citation topics
- 4 Electrical Engineering, Electronics & Computer Science
- 4.116 Robotics
- 4.116.1097 Gesture Recognition
- Web Of Science research areas
- Computer Science, Artificial Intelligence
- ESI research areas
- Engineering