Xinxu Lin ^1,2 Mingxuan Liu ¹ Hong Chen ^1*

• ¹ Tsinghua University, Beijing, China
• ² Fudan University, Shanghai, Shanghai Municipality, China

Event-based cameras are suitable for human action recognition (HAR) by providing movement perception with highly dynamic range, high temporal resolution, high power efficiency and low latency. Spike Neural Networks (SNNs) are naturally suited to deal with the asynchronous and sparse data from the event cameras due to their spike-based event-driven paradigm, with less power consumption compared to artificial neural networks. In this paper, we propose two end-to-end SNNs, namely Spike-HAR and Spike-HAR++, to introduce spiking transformer into event-based HAR. Spike-HAR includes two novel blocks: \textcolor{blue}{a spike attention branch}, which enables model to focus on regions with high spike rates, reducing the impact of noise to improve the accuracy, and a parallel spike transformer block with simplified spiking self-attention mechanism, increasing computational efficiency. To better extract crucial information from high-level features, we modify the architecture of the spike \textcolor{blue}{attention branch} and extend it in Spike-HAR to a higher dimension, proposing Spike-HAR++ to further enhance classification performance. Comprehensive experiments were conducted on four HAR datasets: SL-Animals-DVS, N-LSA64, DVS128 Gesture and DailyAction-DVS, to demonstrate the superior performance of our proposed model. Additionally, the proposed Spike-HAR and Spike-HAR++ require only 0.03 mJ and 0.06 mJ, respectively, to process a sequence of event frames, with model sizes of only 0.7M and 1.8M. This efficiency positions it as a promising new SNN baseline for the HAR community.