.png){kind=icon}
返回
Skeleton-Based Action Recognition With Focusing-Diffusion Graph Convolutional Networks
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2021.3116513.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph Convolutional Networks have been successfully applied in skeleton-based action recognition. The key is fully exploring the spatial-temporal context. This letter proposes a Focusing-Diffusion Graph Convolutional Network (FDGCN) to address this issue. Each skeleton frame is first decomposed into two opposite-direction graphs for subsequent focusing and diffusion processes. Next, the focusing process generates a spatial-level representation for each frame individually by an attention module. This representation is regarded as a supernode to aggregate the feature from each joint node in each frame for spatial context extraction. After generating supernodes for the entire sequence, a transformer encoder layer is proposed to capture the temporal context further. Finally, these supernodes pass the embedded spatial-temporal context back to the spatial joints through the diffusion graph in the diffusing process. Extensive experiments on the NTU RGB+D and Skeleton-Kinetics benchmarks demonstrate the effectiveness of our approach.
Keyword:
Focusing
Convolution
Skeleton
Transformers
Hidden Markov models
Context modeling
Aggregates
Focusing and diffusion
bidirectional attention
graph convolutional network
action recognition
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Enhanced skeleton visualization for view invariant human action recognition用于视图不变人体动作识别的增强骨架可视化.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容