.png){kind=icon}
.png){kind=icon}
Return
Multi-scale sampling attention graph convolutional networks for skeleton-based action recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2024.128086.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Skeleton-based action recognition has attracted increasing interest in recent years. With the flexibility of modeling long-range dependency of joints, the self-attention module has served as the basic component in skeleton-based action recognition. However, the global receptive field of self-attention is not conducive to the modeling of skeleton locality, and the self-attention model is imbued with less inductive bias, which leads to overfitting. In this paper, we propose an attention graph convolutional network (AGCN) with multi- scale sampling to effectively model the local and global features of the skeleton. Firstly, we propose two extreme sampling strategies for generating and ordering neighboring nodes of root nodes. A local-first sampling method is introduced to construct local graph windows, and a global-first sampling method is proposed to assemble long-range joints for constructing global graph windows. The local-first sampling and global-first sampling introduce more skeleton-specific inductive biases to regularize the model capacity. Secondly, the AGCN combines the self-attention mechanism with graph convolution operation, which alleviates the over- smoothing of graph convolution and preserves the translation invariant. Based on the multi-scale sampling strategy, the AGCN can effectively model the locality and non-locality of the skeleton. Finally, by coupling the aforementioned proposals, we develop a two-pathway model for multi-scale feature fusion. Extensive experiments demonstrate that our model could achieve comparable performance with state-of-the-art works on the NTU RGB+D 60, NTU RGB+D 120, the UAV-HUMAN and NW-UCLA datasets.
Keywords:
Skeleton-based action recognition
Multi-scale sampling
Self-attention
Graph convolutional network
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
