# Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras

Source: [Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras](<https://www.sota2.com/research/paper/690442663ef7ccd74e5e499a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-11-01T05:01:40.642Z

Authors: Christoffer Koo {\\O}hrstr{\\o}m, Ronja G\\"uldenring, Lazaros Nalpantidis

Published: 2025-10-30T15:40:34.000Z

## Abstract

We propose tokenization of events and present a tokenizer, Spiking Patches, specifically designed for event cameras. Given a stream of asynchronous and spatially sparse events, our goal is to discover an event representation that preserves these properties. Prior works have represented events as frames or as voxels. However, while these representations yield high accuracy, both frames and voxels are synchronous and decrease the spatial sparsity. Spiking Patches gives the means to preserve the unique properties of event cameras and we show in our experiments that this comes without sacrificing accuracy. We evaluate our tokenizer using a GNN, PCN, and a Transformer on gesture recognition and object detection. Tokens from Spiking Patches yield inference times that are up to 3.4x faster than voxel-based tokens and up to 10.4x faster than frames. We achieve this while matching their accuracy and even surpassing in some cases with absolute improvements up to 3.8 for gesture recognition and up to 1.4 for object detection. Thus, tokenization constitutes a novel direction in event-based vision and marks a step towards methods that preserve the properties of event cameras.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.26614>)

[PDF](<https://arxiv.org/pdf/2510.26614.pdf>)
