# Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras

arXiv: https://arxiv.org/abs/2501.01040 · HTML: https://mlsanity.com/paper/2501.01040/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jan 2025.

## Built on by (most cited first, 4 of 4)

- [EV-Flying: an Event-based Dataset for In-The-Wild Recognition of Flying Objects](https://mlsanity.com/paper/2506.04048/) (2025)
- [Event2Vec: Processing Neuromorphic Events Directly by Representations in Vector Space](https://mlsanity.com/paper/2504.15371/) (2025)
- [SMV-EAR: Bring Spatiotemporal Multi-View Representation Learning into Efficient Event-Based Action Recognition](https://mlsanity.com/paper/2601.17391/) (2026)
- [Event-based Action Recognition by Pre-Training on Multi-Frame Representations](https://mlsanity.com/paper/2610.13856/) (2026)

## Abstract (arXiv)

Dynamic vision sensors (DVS) are bio-inspired devices that capture visual information in the form of asynchronous events, which encode changes in pixel intensity with high temporal resolution and low latency. These events provide rich motion cues that can be exploited for various computer vision tasks, such as action recognition. However, most existing DVS-based action recognition methods lose temporal information during data transformation or suffer from noise and outliers caused by sensor imperfections or environmental factors. To address these challenges, we propose a novel framework that preserves and exploits the spatiotemporal structure of event data for action recognition. Our framework consists of two main components: 1) a point-wise event masked autoencoder (MAE) that learns a compact and discriminative representation of event patches by reconstructing them from masked raw event camera points data; 2) an improved event points patch generation algorithm that leverages an event data inlier model and point-wise data augmentation techniques to enhance the quality and diversity of event points patches. To the best of our knowledge, our approach introduces the pre-train method into event camera raw points data for the first time, and we propose a novel event points patch embedding to utilize transformer-based models on event cameras.