GAS-GCN: Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition

Skeleton-based action recognition has achieved great advances with the development of graph convolutional networks (GCNs). Many existing GCNs-based models only use the fixed hand-crafted adjacency matrix to describe the connections between human body joints. This omits the important implicit connect...

Descripción completa

Detalles Bibliográficos
Autores principales: Chan, Wensong, Tian, Zhiqiang, Wu, Yang
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7349730/
https://www.ncbi.nlm.nih.gov/pubmed/32575802
http://dx.doi.org/10.3390/s20123499

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7349730/
https://www.ncbi.nlm.nih.gov/pubmed/32575802
http://dx.doi.org/10.3390/s20123499

Ejemplares similares