mlsanityData to 14 Oct 2026

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

arXiv 2510.26614 ↗First posted 30 Oct 2025cs.CV cs.ROcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 30 Oct 2025.

Builds on

33 of 44 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  6. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  7. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  8. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  9. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  10. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 724
  11. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  12. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 266
21 more
  1. 2019End-to-End Learning of Representations for Asynchronous Event-Based Datacited by 217
  2. 2016Training Deep Spiking Neural Networks using Backpropagationcited by 205
  3. 2020Learning to Detect Objects with a 1 Megapixel Event Cameracited by 186
  4. 2022Recurrent Vision Transformers for Object Detection with Event Camerascited by 159
  5. 2022AEGNN: Asynchronous Event-based Graph Neural Networkscited by 118
  6. 2020A Large Scale Event-based Detection Dataset for Automotivecited by 109
  7. 2020Event-based Asynchronous Sparse Convolutional Networkscited by 104
  8. 2024State Space Models for Event Camerascited by 75
  9. 2021Time-Ordered Recent Event (TORE) Volumes for Event Camerascited by 73
  10. 2023GET: Group Event Transformer for Event-Based Visioncited by 73
  11. 2018EventNet: Asynchronous Recursive Event Processingcited by 58
  12. 2022Neuromorphic Data Augmentation for Training Spiking Neural Networkscited by 52
  13. 2023From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detectioncited by 52
  14. 2023Graph-based Asynchronous Event Processing for Rapid Object Recognitioncited by 51
  15. 2022Event Transformer. A sparse-aware solution for efficient event data processingcited by 50
  16. 2024Scene Adaptive Sparse Transformer for Event-based Object Detectioncited by 39
  17. 2021A Voxel Graph CNN for Object Classification with Event Camerascited by 38
  18. 2021EventDrop: data augmentation for event-based learningcited by 28
  19. 2022Exploiting Spatial Sparsity for Event Cameras with Visual Transformerscited by 23
  20. 2022Event Transformer+. A multi-purpose solution for efficient event data processingcited by 13
  21. 2023TTPOINT: A Tensorized Point Cloud Network for Lightweight Action Recognition with Event Camerascited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, Generalcited by 0
  2. 2026Neural Events: Discrete Asynchronous Autoencoders for Event-Based Visioncited by 0