# Event Transformer+. A multi-purpose solution for efficient event data processing

arXiv: https://arxiv.org/abs/2211.12222 · HTML: https://mlsanity.com/paper/2211.12222/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 22 Nov 2022.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion](https://mlsanity.com/paper/1812.08156/) (2018)
- [SLAYER: Spike Layer Error Reassignment in Time](https://mlsanity.com/paper/1810.08646/) (2018)
- [The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception](https://mlsanity.com/paper/1801.10202/) (2018)
- [Video to Events: Recycling Video Datasets for Event Cameras](https://mlsanity.com/paper/1912.03095/) (2019)
- [Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High Speed Scenarios](https://mlsanity.com/paper/1709.06310/) (2017)
- [Delving Deep into Label Smoothing](https://mlsanity.com/paper/2011.12562/) (2020)
- [Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction](https://mlsanity.com/paper/2102.09320/) (2021)
- [Graph-Based Object Classification for Neuromorphic Vision Sensing](https://mlsanity.com/paper/1908.06648/) (2019)
- [Learning Monocular Dense Depth from Events](https://mlsanity.com/paper/2010.08350/) (2020)
- [Time-Ordered Recent Event (TORE) Volumes for Event Cameras](https://mlsanity.com/paper/2103.06108/) (2021)
- [EventNet: Asynchronous Recursive Event Processing](https://mlsanity.com/paper/1812.07045/) (2018)
- [Temporal Binary Representation for Event-Based Action Recognition](https://mlsanity.com/paper/2010.08946/) (2020)
- [Event Transformer. A sparse-aware solution for efficient event data processing](https://mlsanity.com/paper/2204.03355/) (2022)
- [EventHands: Real-Time Neural 3D Hand Pose Estimation from an Event Stream](https://mlsanity.com/paper/2012.06475/) (2020)
- [TUM-VIE: The TUM Stereo Visual-Inertial Event Dataset](https://mlsanity.com/paper/2108.07329/) (2021)
- [Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation](https://mlsanity.com/paper/2109.01801/) (2021)
- [EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow, Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with Monocular or Stereo Algorithms](https://mlsanity.com/paper/2205.03467/) (2022)
- [Differentiable Event Stream Simulator for Non-Rigid 3D Tracking](https://mlsanity.com/paper/2104.15139/) (2021)
- [Representation Learning for Event-based Visuomotor Policies](https://mlsanity.com/paper/2103.00806/) (2021)
- [Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception](https://mlsanity.com/paper/2110.04988/) (2021)
- [Spatiotemporal Filtering for Event-Based Action Recognition](https://mlsanity.com/paper/1903.07067/) (2019)
- [The GRIFFIN Perception Dataset: Bridging the Gap Between Flapping-Wing Flight and Robotic Perception](https://mlsanity.com/paper/2101.10371/) (2021)

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

- [EventHDR: from Event to High-Speed HDR Videos and Beyond](https://mlsanity.com/paper/2409.17029/) (2024)
- [ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data](https://mlsanity.com/paper/2402.01393/) (2024)
- [Learning to Estimate Two Dense Depths from LiDAR and Event Data](https://mlsanity.com/paper/2302.14444/) (2023)
- [EventVGGT: Exploring Cross-Modal Distillation for Consistent Event-based Depth Estimation](https://mlsanity.com/paper/2603.09385/) (2026)
- [EventSleep: Sleep Activity Recognition with Event Cameras](https://mlsanity.com/paper/2404.01801/) (2024)
- [Event2Vec: Processing Neuromorphic Events Directly by Representations in Vector Space](https://mlsanity.com/paper/2504.15371/) (2025)
- [UniCT Depth: Event-Image Fusion Based Monocular Depth Estimation with Convolution-Compensated ViT Dual SA Block](https://mlsanity.com/paper/2507.19948/) (2025)
- [Fast Feature Field (F3): A Predictive Representation of Events](https://mlsanity.com/paper/2509.25146/) (2025)
- [Spiking Patches: Asynchronous, Sparse, and Efficient Tokens for Event Cameras](https://mlsanity.com/paper/2510.26614/) (2025)
- [PASS: Path-selective State Space Model for Event-based Recognition](https://mlsanity.com/paper/2409.16953/) (2024)
- [DELTA: Dense Depth from Events and LiDAR using Transformer's Attention](https://mlsanity.com/paper/2505.02593/) (2025)
- [Stealth Is a Relation, Not a Property: How Event Representations Create Blind Spots for Timing Attacks in Event-Based Perception](https://mlsanity.com/paper/2609.36386/) (2026)
- [SFE-VGGT: Source-Free VGGT Distillation for Event-Based Monocular Depth Estimation](https://mlsanity.com/paper/2609.36929/) (2026)

## Abstract (arXiv)

Event cameras record sparse illumination changes with high temporal resolution and high dynamic range. Thanks to their sparse recording and low consumption, they are increasingly used in applications such as AR/VR and autonomous driving. Current topperforming methods often ignore specific event-data properties, leading to the development of generic but computationally expensive algorithms, while event-aware methods do not perform as well. We propose Event Transformer+, that improves our seminal work EvT with a refined patch-based event representation and a more robust backbone to achieve more accurate results, while still benefiting from event-data sparsity to increase its efficiency. Additionally, we show how our system can work with different data modalities and propose specific output heads, for event-stream classification (i.e. action recognition) and per-pixel predictions (dense depth estimation). Evaluation results show better performance to the state-of-the-art while requiring minimal computation resources, both on GPU and CPU.