An Improved Graph Pooling Network for Skeleton-Based Action Recognition
This work addresses a domain-specific problem in skeleton-based action recognition for computer vision researchers, offering incremental improvements through novel pooling and fusion techniques.
The paper tackles the challenge of applying pooling strategies to skeleton graph modeling for action recognition by proposing an Improved Graph Pooling Network (IGPN) with region-awareness pooling and information preservation modules, achieving a significant accuracy improvement and a 70% reduction in Flops on the NTU-RGB+D 60 dataset.
Pooling is a crucial operation in computer vision, yet the unique structure of skeletons hinders the application of existing pooling strategies to skeleton graph modelling. In this paper, we propose an Improved Graph Pooling Network, referred to as IGPN. The main innovations include: Our method incorporates a region-awareness pooling strategy based on structural partitioning. The correlation matrix of the original feature is used to adaptively adjust the weight of information in different regions of the newly generated features, resulting in more flexible and effective processing. To prevent the irreversible loss of discriminative information, we propose a cross fusion module and an information supplement module to provide block-level and input-level information respectively. As a plug-and-play structure, the proposed operation can be seamlessly combined with existing GCN-based models. We conducted extensive evaluations on several challenging benchmarks, and the experimental results indicate the effectiveness of our proposed solutions. For example, in the cross-subject evaluation of the NTU-RGB+D 60 dataset, IGPN achieves a significant improvement in accuracy compared to the baseline while reducing Flops by nearly 70%; a heavier version has also been introduced to further boost accuracy.