# Spatiotemporal Filtering for Event-Based Action Recognition

arXiv: https://arxiv.org/abs/1903.07067 · HTML: https://mlsanity.com/paper/1903.07067/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2019.

## Built on by (most cited first, 13 of 13)

- [Event Transformer. A sparse-aware solution for efficient event data processing](https://mlsanity.com/paper/2204.03355/) (2022)
- [CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processor](https://mlsanity.com/paper/2107.00401/) (2021)
- [Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networks](https://mlsanity.com/paper/2110.08858/) (2021)
- [Hypergraph-based Multi-View Action Recognition using Event Cameras](https://mlsanity.com/paper/2403.19316/) (2024)
- [Event Transformer+. A multi-purpose solution for efficient event data processing](https://mlsanity.com/paper/2211.12222/) (2022)
- [EventTransAct: A video transformer-based framework for Event-camera based action recognition](https://mlsanity.com/paper/2308.13711/) (2023)
- [EV-Flying: an Event-based Dataset for In-The-Wild Recognition of Flying Objects](https://mlsanity.com/paper/2506.04048/) (2025)
- [Neuromorphic High-Frequency 3D Dancing Pose Estimation in Dynamic Environment](https://mlsanity.com/paper/2301.06648/) (2023)
- [Ultra-low Latency Spiking Neural Networks with Spatio-Temporal Compression and Synaptic Convolutional Block](https://mlsanity.com/paper/2203.10006/) (2022)
- [EventSleep: Sleep Activity Recognition with Event Cameras](https://mlsanity.com/paper/2404.01801/) (2024)
- [Neural Ganglion Sensors: Learning Task-specific Event Cameras Inspired by the Neural Circuit of the Human Retina](https://mlsanity.com/paper/2504.13457/) (2025)
- [EHWGesture -- A dataset for multimodal understanding of clinical gestures](https://mlsanity.com/paper/2509.07525/) (2025)
- [HabitAction: A Video Dataset for Human Habitual Behavior Recognition](https://mlsanity.com/paper/2408.13463/) (2024)

## Abstract (arXiv)

In this paper, we address the challenging problem of action recognition, using event-based cameras. To recognise most gestural actions, often higher temporal precision is required for sampling visual information. Actions are defined by motion, and therefore, when using event-based cameras it is often unnecessary to re-sample the entire scene. Neuromorphic, event-based cameras have presented an alternative to visual information acquisition by asynchronously time-encoding pixel intensity changes, through temporally precise spikes (10 micro-second resolution), making them well equipped for action recognition. However, other challenges exist, which are intrinsic to event-based imagers, such as higher signal-to-noise ratio, and a spatiotemporally sparse information. One option is to convert event-data into frames, but this could result in significant temporal precision loss. In this work we introduce spatiotemporal filtering in the spike-event domain, as an alternative way of channeling spatiotemporal information through to a convolutional neural network. The filters are local spatiotemporal weight matrices, learned from the spike-event data, in an unsupervised manner. We find that appropriate spatiotemporal filtering significantly improves CNN performance beyond state-of-the-art on the event-based DVS Gesture dataset. On our newly recorded action recognition dataset, our method shows significant improvement when compared with other, standard ways of generating the spatiotemporal filters.