Multidimensional Refinement Graph Convolutional Network With Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition

Shenglan Liu

doi:10.1109/TNNLS.2024.3384770

Multidimensional Refinement Graph Convolutional Network With Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition

2024-01-01

0

OA

AI

DOI：10.1109/TNNLS.2024.3384770

原文链接

原文求助

摘要

En 中文

Graph convolutional networks (GCNs) have been widely used in skeleton-based action recognition. However, existing approaches are limited in fine-grained action recognition due to the similarity of interclass data. Moreover, the noisy data from pose extraction increase the challenge of fine-grained recognition. In this work, we propose a flexible attention block called channel-variable spatial-temporal attention (CVSTA) to enhance the discriminative power of spatial-temporal joints and obtain a more compact intraclass feature distribution. Based on CVSTA, we construct a multidimensional refinement GCN (MDR-GCN) that can improve the discrimination among channel-, joint-, and frame-level features for fine-grained actions. Furthermore, we propose a robust decouple loss (RDL) that significantly boosts the effect of the CVSTA and reduces the impact of noise. The proposed method combining MDR-GCN with RDL outperforms the known state-of-the-art skeleton-based approaches on fine-grained datasets, FineGym99 and FSD-10, and also on the coarse NTU-RGB + D 120 dataset and NTU-RGB + D X-view version. Our code is publicly available at https://github.com/dingyn-Reno/MDR-GCN.

Keyword:

Task analysis

Convolution

Skeleton

Robustness

Feature extraction

Topology

Convolutional neural networks

Fine-grained action

graph convolutional network (GCN)

robust decouple loss (RDL)

spatial-temporal attention

Multidimensional Refinement Graph Convolutional Network With Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition

摘要

期刊

机构

引用论文