提出自适应图卷积网络，提升稀疏点云下人体动作识别精度。
Multi-Head Adaptive Graph Convolution Network for Sparse Point Cloud-Based Human Activity Recognition
- 设计多头动态核模块，按局部几何结构自适应调整卷积核
- 在多个基准数据集上达到当前最优性能，准确率超现有方法
- 适合隐私敏感场景的智能机器人动作识别应用
人体动作识别对支持独立生活尤其老年人和需要帮助者至关重要。家用服务机器人具备监控能力可提升安全性和支持水平。尽管图像方法近年进展显著，但受限于隐私顾虑及低光/黑暗环境下的表现，应用仍有限。毫米波雷达生成的点云数据具有隐私保护优势，但处理稀疏噪声点云仍是长期挑战。虽然基于图的方法与注意力机制前景广阔，但多依赖‘固定’卷积核，在所有邻域统一使用，难以匹配局部几何差异，亟需自适应方法实现动态调整。为此，本文在图卷积框架中引入自适应机制，不再使用单一共享权重函数，而是通过多头自适应核（MAK）模块生成多个动态核，分别捕捉局部特征空间的不同方面。通过逐步优化局部特征并保持全局空间上下文，使卷积核能根据局部特征变化自适应调整。在多个基准数据集上的实验结果验证了该方法的有效性，实现了人体动作识别的最先进性能。代码已开源：https://github.com/Gbouna/MAK-GCN
原文摘要 · Abstract (English)
Human activity recognition is increasingly vital for supporting independent living, particularly for the elderly and those in need of assistance. Domestic service robots with monitoring capabilities can enhance safety and provide essential support. Although image-based methods have advanced considerably in the past decade, their adoption remains limited by concerns over privacy and sensitivity to low-light or dark conditions. As an alternative, millimetre-wave (mmWave) radar can produce point cloud data which is privacy-preserving. However, processing the sparse and noisy point clouds remains a long-standing challenge. While graph-based methods and attention mechanisms show promise, they predominantly rely on "fixed" kernels; kernels that are applied uniformly across all neighbourhoods, highlighting the need for adaptive approaches that can dynamically adjust their kernels to the specific geometry of each local neighbourhood in point cloud data. To overcome this limitation, we introduce an adaptive approach within the graph convolutional framework. Instead of a single shared weight function, our Multi-Head Adaptive Kernel (MAK) module generates multiple dynamic kernels, each capturing different aspects of the local feature space. By progressively refining local features while maintaining global spatial context, our method enables convolution kernels to adapt to varying local features. Experimental results on benchmark datasets confirm the effectiveness of our approach, achieving state-of-the-art performance in human activity recognition. Our source code is made publicly available at: https://github.com/Gbouna/MAK-GCN
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。