# Spiking Transformer with Spatial-Temporal Attention

arXiv: https://arxiv.org/abs/2409.19764 · HTML: https://mlsanity.com/paper/2409.19764/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2024.

## Built on by (most cited first, 19 of 19)

- [SpiLiFormer: Enhancing Spiking Transformers with Lateral Inhibition](https://mlsanity.com/paper/2503.15986/) (2025)
- [Hardware, Algorithms, and Applications of the Neuromorphic Vision Sensor: a Review](https://mlsanity.com/paper/2504.08588/) (2025)
- [SNN-Driven Multimodal Human Action Recognition via Sparse Spatial-Temporal Data Fusion](https://mlsanity.com/paper/2502.13385/) (2025)
- [Edge Intelligence with Spiking Neural Networks](https://mlsanity.com/paper/2507.14069/) (2025)
- [Signal-SGN++: Topology-Enhanced Time-Frequency Spiking Graph Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2512.22214/) (2025)
- [ChronoSpike: An Adaptive Spiking Graph Neural Network for Dynamic Graphs](https://mlsanity.com/paper/2602.01124/) (2026)
- [BSViT: A Burst Spiking Vision Transformer for Expressive and Efficient Visual Representation Learning](https://mlsanity.com/paper/2604.23165/) (2026)
- [TDFormer: A Top-Down Attention-Controlled Spiking Transformer](https://mlsanity.com/paper/2505.15840/) (2025)
- [Quantization Meets Spikes: Nearly Lossless Conversion at the First Timestep via Polarity Multi-Spike Mapping](https://mlsanity.com/paper/2508.14520/) (2025)
- [ASecond-Order SpikingSSM for Wearables](https://mlsanity.com/paper/2510.14386/) (2025)
- [Temporal Dynamics Enhancer for Directly Trained Spiking Object Detectors](https://mlsanity.com/paper/2512.02447/) (2025)
- [MD-SNN: Membrane Potential-aware Distillation on Quantized Spiking Neural Network](https://mlsanity.com/paper/2512.04443/) (2025)
- [Towards Green Wearable Computing: A Physics-Aware Spiking Neural Network for Energy-Efficient IMU-based Human Activity Recognition](https://mlsanity.com/paper/2604.10458/) (2026)
- [Benchmarking Fairness in Spiking Neural Networks: Data Bias, Spurious Features, and Hardware Effects](https://mlsanity.com/paper/2605.27407/) (2026)
- [SpikF-GO: Spiking Fourier Graph Operators for Multivariate Time Series Forecasting](https://mlsanity.com/paper/2606.13901/) (2026)
- [Rethinking Attention Locality in Spiking Transformers](https://mlsanity.com/paper/2608.08541/) (2026)
- [Spiking Local Interaction and Adaptive Complementary Fusion for Spiking Transformer](https://mlsanity.com/paper/2608.19238/) (2026)
- [RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision](https://mlsanity.com/paper/2609.32537/) (2026)
- [Neuromorphic Decoding and Dynamical Image Reconstruction from Populations of Spiking Retinal Ganglion Cells](https://mlsanity.com/paper/2610.17154/) (2026)

## Abstract (arXiv)

Spike-based Transformer presents a compelling and energy-efficient alternative to traditional Artificial Neural Network (ANN)-based Transformers, achieving impressive results through sparse binary computations. However, existing spike-based transformers predominantly focus on spatial attention while neglecting crucial temporal dependencies inherent in spike-based processing, leading to suboptimal feature representation and limited performance. To address this limitation, we propose Spiking Transformer with Spatial-Temporal Attention (STAtten), a simple and straightforward architecture that efficiently integrates both spatial and temporal information in the self-attention mechanism. STAtten introduces a block-wise computation strategy that processes information in spatial-temporal chunks, enabling comprehensive feature capture while maintaining the same computational complexity as previous spatial-only approaches. Our method can be seamlessly integrated into existing spike-based transformers without architectural overhaul. Extensive experiments demonstrate that STAtten significantly improves the performance of existing spike-based transformers across both static and neuromorphic datasets, including CIFAR10/100, ImageNet, CIFAR10-DVS, and N-Caltech101. The code is available at https://github.com/Intelligent-Computing-Lab-Yale/STAtten