Global Co-Occurrence Feature and Local Spatial Feature Learning for Skeleton-Based Action Recognition

Recent progress on skeleton-based action recognition has been substantial, benefiting mostly from the explosive development of Graph Convolutional Networks (GCN). However, prevailing GCN-based methods may not effectively capture the global co-occurrence features among joints and the local spatial st...

Descripción completa

Detalles Bibliográficos
Autores principales: Xie, Jun, Xin, Wentian, Liu, Ruyi, Miao, Qiguang, Sheng, Lijie, Zhang, Liang, Gao, Xuesong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2020
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7597279/
https://www.ncbi.nlm.nih.gov/pubmed/33286904
http://dx.doi.org/10.3390/e22101135

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7597279/
https://www.ncbi.nlm.nih.gov/pubmed/33286904
http://dx.doi.org/10.3390/e22101135

Ejemplares similares