# Fire on Motion: Optimizing Video Pass-bands for Efficient Spiking Action Recognition

arXiv: https://arxiv.org/abs/2601.22675 · HTML: https://mlsanity.com/paper/2601.22675/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 21 of 21)

- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Real-world Anomaly Detection in Surveillance Videos](https://mlsanity.com/paper/1801.04264/) (2018)
- [Spikformer: When Spiking Neural Network Meets Transformer](https://mlsanity.com/paper/2209.15425/) (2022)
- [Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning](https://mlsanity.com/paper/2101.10030/) (2021)
- [Spike-driven Transformer](https://mlsanity.com/paper/2307.01694/) (2023)
- [Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips](https://mlsanity.com/paper/2404.03663/) (2024)
- [ACTION-Net: Multipath Excitation for Action Recognition](https://mlsanity.com/paper/2103.07372/) (2021)
- [Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training](https://mlsanity.com/paper/2411.16061/) (2024)
- [HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors](https://mlsanity.com/paper/2211.09648/) (2022)
- [Weakly Supervised Video Anomaly Detection via Center-guided Discriminative Learning](https://mlsanity.com/paper/2104.07268/) (2021)
- [BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation](https://mlsanity.com/paper/2207.08533/) (2022)
- [UCF-Crime-DVS: A Novel Event-Based Dataset for Video Anomaly Detection with Spiking Neural Networks](https://mlsanity.com/paper/2503.12905/) (2025)
- [Inherent Redundancy in Spiking Neural Networks](https://mlsanity.com/paper/2308.08227/) (2023)
- [TIM: An Efficient Temporal Interaction Module for Spiking Transformer](https://mlsanity.com/paper/2401.11687/) (2024)
- [FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networks](https://mlsanity.com/paper/2501.14744/) (2024)
- [Spiking Neural Networks for Temporal Processing: Status Quo and Future Prospects](https://mlsanity.com/paper/2502.09449/) (2025)
- [Enhancing Audio-Visual Spiking Neural Networks through Semantic-Alignment and Cross-Modal Residual Learning](https://mlsanity.com/paper/2502.12488/) (2025)
- [SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition](https://mlsanity.com/paper/2406.15034/) (2024)
- [ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognition](https://mlsanity.com/paper/2409.01564/) (2024)

## Built on by (most cited first, 1 of 1)

- [ENCORE: Event-Assisted Complementary Motion Refinement for Learned Video Compression](https://mlsanity.com/paper/2607.28020/) (2026)

## Abstract (arXiv)

Spiking neural networks (SNNs) have gained traction in vision due to their energy efficiency, bio-plausibility, and inherent temporal processing. Yet, despite this temporal capacity, most progress concentrates on static image benchmarks, and SNNs still underperform on dynamic video tasks compared to artificial neural networks (ANNs). In this work, we diagnose a fundamental pass-band mismatch: Standard spiking dynamics behave as a temporal low pass that emphasizes static content while attenuating motion bearing bands, where task relevant information concentrates in dynamic tasks. This phenomenon explains why SNNs can approach ANNs on static tasks yet fall behind on tasks that demand richer temporal understanding.To remedy this, we propose the Pass-Bands Optimizer (PBO), a plug-and-play module that optimizes the temporal pass-band toward task-relevant motion bands. PBO introduces only two learnable parameters, and a lightweight consistency constraint that preserves semantics and boundaries, incurring negligible computational overhead and requires no architectural changes. PBO deliberately suppresses static components that contribute little to discrimination, effectively high passing the stream so that spiking activity concentrates on motion bearing content. On UCF101, PBO yields over ten percentage points improvement. On more complex multi-modal action recognition and weakly supervised video anomaly detection, PBO delivers consistent and significant gains, offering a new perspective for SNN based video processing and understanding.