Event2Vec: Processing Neuromorphic Events Directly by Representations in Vector Space
Not on the map. Why?
Abstract (arXiv)
Neuromorphic event cameras possess superior temporal resolution, power efficiency, and dynamic range compared to traditional cameras. However, their asynchronous and sparse data format poses a significant challenge for conventional deep learning methods. Most existing methods either densify events into frames, sacrificing their sparse asynchronous nature, or use irregular models that are less compatible with GPU acceleration. Inspired by word-to-vector models, we propose event2vec, a novel representation that allows Transformers to process events directly. We demonstrate the effectiveness of event2vec on the DVS Gesture, ASL-DVS, and DVS-Lip benchmarks, showing that event2vec is remarkably parameter-efficient, features high throughput and low latency, and achieves high accuracy even with an extremely low number of events or low spatial resolutions. These results show that sparse asynchronous event data can be directly integrated into high-throughput Transformer architectures, offering an efficient paradigm for real-time neuromorphic vision. The code is provided at https://github.com/Intelligent-Computing-Lab-Panda/event2vec.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 52 of its 94 references that are in the map. First posted on arXiv 21 Apr 2025.
Builds on
52 of 94 references.
References · 52
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2024The Llama 3 Herd of Modelscited by 14,715
- 2016Layer Normalizationcited by 5,669
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
- 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
38 more
- 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,474
- 2017Billion-scale similarity search with GPUscited by 2,497
- 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
- 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 2,022
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
- 2018Group Normalizationcited by 1,524
- 2016Understanding intermediate layers using linear classifier probescited by 1,353
- 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
- 2019Event-based Vision: A Surveycited by 1,016
- 2023RWKV: Reinventing RNNs for the Transformer Eracited by 827
- 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
- 2023Retentive Network: A Successor to Transformer for Large Language Modelscited by 613
- 2023Gated Linear Attention Transformers with Hardware-Efficient Trainingcited by 514
- 2021Deep Residual Learning in Spiking Neural Networkscited by 331
- 2018Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotioncited by 307
- 2019Revisiting Graph Neural Networks: All We Have is Low-Pass Filterscited by 261
- 2018HATS: Histograms of Averaged Time Surfaces for Robust Event-based Object Classificationcited by 218
- 2019End-to-End Learning of Representations for Asynchronous Event-Based Datacited by 217
- 2016FractalNet: Ultra-Deep Neural Networks without Residualscited by 216
- 2019Events-to-Video: Bringing Modern Computer Vision to Event Camerascited by 193
- 2023SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligencecited by 169
- 2019Modeling Point Clouds with Self-Attention and Gumbel Subset Samplingcited by 151
- 2022AEGNN: Asynchronous Event-based Graph Neural Networkscited by 118
- 2022Attention Spiking Neural Networkscited by 107
- 2020Event-based Asynchronous Sparse Convolutional Networkscited by 104
- 2019Graph-Based Object Classification for Neuromorphic Vision Sensingcited by 85
- 2022Object Detection with Spiking Neural Networks on Automotive Event Datacited by 80
- 2023GET: Group Event Transformer for Event-Based Visioncited by 73
- 2018EventNet: Asynchronous Recursive Event Processingcited by 58
- 2025Forgetting Transformer: Softmax Attention with a Forget Gatecited by 53
- 2023Speck: A Smart event-based Vision Sensor with a low latency 327K Neuron Convolutional Neuronal Network Processing Pipelinecited by 52
- 2022Efficient recurrent architectures through activity sparsity and sparse back-propagation through timecited by 26
- 2024Direct Training High-Performance Deep Spiking Neural Networks: A Review of Theories and Methodscited by 25
- 2024Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMambacited by 19
- 2022Event Transformer+. A multi-purpose solution for efficient event data processingcited by 13
- 2022Bina-Rep Event Frames: a Simple and Effective Representation for Event-based camerascited by 12
- 2023E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learningcited by 11
- 2023Learning Bottleneck Transformer for Event Image-Voxel Feature Fusion based Classificationcited by 6
50 most cited of 52 All 52 (JSON)
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.