cs.LGNov 9, 2026

TSFFormer: A Frequency-Domain Spike Transformer for Green Human Activity Recognition

Authors: Jiale Deng, Shuiying Xiang

Organizations: Xidian University, Xi’an 710071, China

Abstract

Wearable Inertial Measurement Units (IMUs) enable pervasive Human Activity Recognition (HAR), but traditional Deep Neural Networks (DNNs) suffer from an "arithmetic-latency deadlock" due to dense floating-point MAC operations. While Spiking Neural Networks (SNNs) offer ultra-low power, existing ones face spatial blind spots, rigid neurons, and gradient degradation. To address these, we propose TSFFormer, a purely spiking Fourier Transformer for Green HAR. It introduces two key innovations: (1) a MultiHeadFourier attention that performs frequency-domain global mixing, reducing complexity from O(V2)O(V^2) to O(Vlog⁡V)O(V\log V), eliminating spatial blind spots, and saving ∼\sim50% GPU memory; and (2) a dual-compartment Temporal Spiking LIF (TSLIFNode) that utilizes dynamic thresholds to adapt to non-stationary rhythms and mitigate gradient degradation. Extensive experiments on 8 public IMU benchmarks demonstrate that TSFFormer surpasses state-of-the-art SNNs and even the classic DeepConvLSTM, achieving a ∼\sim3×\times faster training speed with an energy footprint of 0.1 pJ. Ablation studies confirm the synergistic effect of our modules, providing a highly accurate, ultra-low-power event-driven paradigm for wearable sensing.

Figures & tables

Explore similar work

CardsList
  1. Towards Green Wearable Computing: A Physics-Aware Spiking Neural Network for Energy-Efficient IMU-based Human Activity Recognition

    Apr 12, 2026Naichuan Zheng, Hailun Xia, Zepeng Sun +2Spiking Neural NetworksHuman Activity Recognition

  2. S3T-Former: A Purely Spike-Driven State-Space Topology Transformer for Skeleton Action Recognition

    Mar 18, 2026Naichuan Zheng, Hailun Xia, Zepeng Sun +2Skeleton-Based Action RecognitionSpiking Transformers

  3. SAFformer:Improving Spiking Transformer via Active Predictive Filtering

    May 8, 2026Zequan Xie, Weiming Zeng, Yunhua Chen +3Spiking TransformersEfficient ViTs