AI 中文总结
针对跌倒冲击检测问题，提出FLASH框架，集成单矩阵超图表示与Mamba模型，通过自适应反馈机制，构建生物力学超边捕捉关节协调与时间动态，实验证明其精度高、能实时推理且泛化能力强，还降低计算成本并提供可解释反馈。
AI 中文摘要
跌倒是一项重大的公共卫生挑战，准确检测个体撞击地面的冲击时刻对于及时干预至关重要。现有的基于骨架的方法仅依靠图神经网络对成对关节连接进行建模，无法捕捉跌倒冲击的多关节协调特征，而基于Transformer的时间模型具有二次复杂度，限制了实时部署。我们提出了FLASH，这是一个通过自适应反馈机制将单矩阵超图表示与Mamba的选择性状态空间模型相结合的新颖框架，用于高效冲击检测。我们的方法构建了基于生物力学的超边来对功能关节协调进行建模，同时利用Mamba的线性时间复杂度来捕捉时间动态。在UP-Fall和UMAFall数据集上的实验表明，FLASH实现了具有实时推理能力和强大的零样本跨数据集泛化能力的最优精度，同时与基于双表示和Transformer的方法相比，显著降低了计算成本。该模型通过与生物力学原理一致的学习注意力模式提供可解释的反馈。代码可在此https URL获取。
英文摘要
Falls represent a critical public health challenge, and accurate detection of the impact moment when an individual hits the ground is crucial for timely intervention. Existing skeleton-based methods rely on graph neural networks modeling only pairwise joint connections, failing to capture multi-joint coordination characteristic of fall impacts, while transformer-based temporal models suffer from quadratic complexity limiting real-time deployment. We propose FLASH, a novel framework integrating single-matrix hypergraph representations with Mamba's selective state-space models through adaptive feedback mechanisms for efficient impact detection. Our approach constructs biomechanically-grounded hyperedges to model functional joint coordination while leveraging Mamba's linear-time complexity to capture temporal dynamics. Experiments on UP-Fall and UMAFall datasets demonstrate that FLASH achieves state-of-the-art accuracy with real-time inference capability and strong zero-shot cross-dataset generalization, while significantly reducing computational cost compared to dual-representation and transformer-based methods. The model provides interpretable feedback through learned attention patterns aligned with biomechanical principles. Code is available at https://github.com/Tresor-Koffi/FLASH-Impact-Fall-Detection.
Comments6 pages, 2 figures. Accepted at IEEE International Conference on Image Processing (ICIP 2026), to appear September 2026
