Cargando…
Adaptive Attention Memory Graph Convolutional Networks for Skeleton-Based Action Recognition
Graph Convolutional Networks (GCNs) have attracted a lot of attention and shown remarkable performance for action recognition in recent years. For improving the recognition accuracy, how to build graph structure adaptively, select key frames and extract discriminative features are the key problems o...
Autores principales: | Liu, Di, Xu, Hui, Wang, Jianzhong, Lu, Yinghua, Kong, Jun, Qi, Miao |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8538327/ https://www.ncbi.nlm.nih.gov/pubmed/34695972 http://dx.doi.org/10.3390/s21206761 |
Ejemplares similares
-
Whole and Part Adaptive Fusion Graph Convolutional Networks for Skeleton-Based Action Recognition
por: Zuo, Qi, et al.
Publicado: (2020) -
Shallow Graph Convolutional Network for Skeleton-Based Action Recognition
por: Yang, Wenjie, et al.
Publicado: (2021) -
Multi-scale and attention enhanced graph convolution network for skeleton-based violence action recognition
por: Yang, Huaigang, et al.
Publicado: (2022) -
Multi-Modality Adaptive Feature Fusion Graph Convolutional Network for Skeleton-Based Action Recognition
por: Zhang, Haiping, et al.
Publicado: (2023) -
GAS-GCN: Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition
por: Chan, Wensong, et al.
Publicado: (2020)