用双曲几何提升骨骼动作识别效率，降低计算开销。
HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition
- 将骨骼数据映射到双曲空间，利用双曲线性注意力建模层级结构。
- 在NTU RGB+D和120数据集上，计算量显著下降且精度保持稳定。
- 适合对实时性要求高的动作识别场景，如智能监控、可穿戴设备。
Transformer在基于骨骼的人体动作识别中表现优异，但其二次计算复杂度限制了实际应用。为缓解此问题，已有研究探索线性注意力机制，但难以捕捉骨骼数据的层次结构。双曲几何中的庞加莱模型能有效建模层级结构，但现有主流线性注意力缺乏适配的双曲运算。本文提出HyLiFormer，一种专用于骨骼动作识别的双曲线性注意力Transformer。方法包含超曲率变换模块（HTC），将骨骼数据映射至双曲空间，并设计双曲线性注意力模块（HLA）以高效建模长程依赖。理论分析与大量实验在NTU RGB+D和NTU RGB+D 120数据集上表明，HyLiFormer显著降低计算复杂度的同时保持模型精度，是高效关键应用场景的有力解决方案。
原文摘要 · Abstract (English)
Transformers have demonstrated remarkable performance in skeleton-based human action recognition, yet their quadratic computational complexity remains a bottleneck for real-world applications. To mitigate this, linear attention mechanisms have been explored but struggle to capture the hierarchical structure of skeleton data. Meanwhile, the Poincaré model, as a typical hyperbolic geometry, offers a powerful framework for modeling hierarchical structures but lacks well-defined operations for existing mainstream linear attention. In this paper, we propose HyLiFormer, a novel hyperbolic linear attention Transformer tailored for skeleton-based action recognition. Our approach incorporates a Hyperbolic Transformation with Curvatures (HTC) module to map skeleton data into hyperbolic space and a Hyperbolic Linear Attention (HLA) module for efficient long-range dependency modeling. Theoretical analysis and extensive experiments on NTU RGB+D and NTU RGB+D 120 datasets demonstrate that HyLiFormer significantly reduces computational complexity while preserving model accuracy, making it a promising solution for efficiency-critical applications.
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。