# A Spatial-channel-temporal-fused Attention for Spiking Neural Networks

arXiv: https://arxiv.org/abs/2209.10837 · HTML: https://mlsanity.com/paper/2209.10837/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 88 references that are in the map.
- First posted on arXiv 22 Sep 2022.

## Builds on (most cited first, 30 of 34)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [Direct Training for Spiking Neural Networks: Faster, Larger, Better](https://mlsanity.com/paper/1809.05793/) (2018)
- [SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning](https://mlsanity.com/paper/1611.05594/) (2016)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/1903.06530/) (2019)
- [An End-to-End Spatio-Temporal Attention Model for Human Action Recognition from Skeleton Data](https://mlsanity.com/paper/1611.06067/) (2016)
- [Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional Networks](https://mlsanity.com/paper/1803.02579/) (2018)
- [Temporal-wise Attention Spiking Neural Networks for Event Streams Classification](https://mlsanity.com/paper/2107.11711/) (2021)
- [Time-Ordered Recent Event (TORE) Volumes for Event Cameras](https://mlsanity.com/paper/2103.06108/) (2021)
- [LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing](https://mlsanity.com/paper/2011.06176/) (2020)
- [Event Transformer. A sparse-aware solution for efficient event data processing](https://mlsanity.com/paper/2204.03355/) (2022)
- [Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization](https://mlsanity.com/paper/1911.00822/) (2019)
- [Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences](https://mlsanity.com/paper/2005.02183/) (2020)
- [Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification](https://mlsanity.com/paper/1708.02286/) (2017)
- [TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks](https://mlsanity.com/paper/2206.10177/) (2022)
- [Brain-inspired global-local learning incorporated with neuromorphic computing](https://mlsanity.com/paper/2006.03226/) (2020)
- [EventDrop: data augmentation for event-based learning](https://mlsanity.com/paper/2106.05836/) (2021)
- [DashNet: A Hybrid Artificial and Spiking Neural Network for High-speed Object Tracking](https://mlsanity.com/paper/1909.12942/) (2019)
- [Hierarchical LSTMs with Adaptive Attention for Visual Captioning](https://mlsanity.com/paper/1812.11004/) (2018)

## Built on by (most cited first, 7 of 7)

- [STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks](https://mlsanity.com/paper/2503.02689/) (2025)
- [Reliable Object Tracking by Multimodal Hybrid Feature Extraction and Transformer-Based Fusion](https://mlsanity.com/paper/2405.17903/) (2024)
- [Tensor Decomposition Based Attention Module for Spiking Neural Networks](https://mlsanity.com/paper/2310.14576/) (2023)
- [EventRPG: Event Data Augmentation with Relevance Propagation Guidance](https://mlsanity.com/paper/2403.09274/) (2024)
- [NiSNN-A: Non-iterative Spiking Neural Networks with Attention with Application to Motor Imagery EEG Classification](https://mlsanity.com/paper/2312.05643/) (2023)
- [A dynamic vision sensor object recognition model based on trainable event-driven convolution and spiking attention mechanism](https://mlsanity.com/paper/2409.12691/) (2024)
- [ST-FlowNet: An Efficient Spiking Neural Network for Event-Based Optical Flow Estimation](https://mlsanity.com/paper/2503.10195/) (2025)

## Abstract (arXiv)

Spiking neural networks (SNNs) mimic brain computational strategies, and exhibit substantial capabilities in spatiotemporal information processing. As an essential factor for human perception, visual attention refers to the dynamic process for selecting salient regions in biological vision systems. Although visual attention mechanisms have achieved great success in computer vision applications, they are rarely introduced into SNNs. Inspired by experimental observations on predictive attentional remapping, we propose a new spatial-channel-temporal-fused attention (SCTFA) module that can guide SNNs to efficiently capture underlying target regions by utilizing accumulated historical spatial-channel information in the present study. Through a systematic evaluation on three event stream datasets (DVS Gesture, SL-Animals-DVS and MNIST-DVS), we demonstrate that the SNN with the SCTFA module (SCTFA-SNN) not only significantly outperforms the baseline SNN (BL-SNN) and two other SNN models with degenerated attention modules, but also achieves competitive accuracy with existing state-of-the-art methods. Additionally, our detailed analysis shows that the proposed SCTFA-SNN model has strong robustness to noise and outstanding stability when faced with incomplete data, while maintaining acceptable complexity and efficiency. Overall, these findings indicate that incorporating appropriate cognitive mechanisms of the brain may provide a promising approach to elevate the capabilities of SNNs.