Research map / Architectures and efficiency / Spiking networks
Event-camera spiking networks
Processes event-camera data asynchronously with spiking and point-based neural networks.
13 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2017–2026) · an approach in Spiking networks, keyword cluster “snn · energy · ann”
State History Tried Checklist Preprints Who Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
4 papers in 2023–24 and 6 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 5.5% to 3.9%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2017 · A Low Power, Fully Event-Based Gesture Recognition System (CVPR 2017 · 978 citations)
- 2019 · EventNet: Asynchronous Recursive Event Processing (CVPR 2019 · 112 citations)
- 2022 · Event-Based Video Reconstruction via Potential-Assisted Spiking Neural Network (CVPR 2022 · 121 citations)
- 2024 · Finding Visual Saliency in Continuous Spike Stream (AAAI 2024 · 6 citations)
- 2025 · Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · 3 citations)
- 2026 · EvReflection: Event-Driven Micro-Dynamics for Reflection Removal (ICML 2026 · 0 citations)
Earliest papers here
- A Low Power, Fully Event-Based Gesture Recognition System (CVPR 2017 · 978 citations)
- EventNet: Asynchronous Recursive Event Processing (CVPR 2019 · 112 citations)
- Event-Based Video Reconstruction via Potential-Assisted Spiking Neural Network (CVPR 2022 · 121 citations)
What has been tried
8 papers here report 95 measured changes (a component added, removed or swapped, compared with a baseline): helped 61%, no clear effect 1%, hurt 38%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Use reverse recurrent mode, fusing step t+1 features into the current features | SVS, multi-step · MAE | 0.0581 -> 0.0554 | Helped | Finding Visual Saliency in Continuous Spike Stream (AAAI 2024 · 6 citations) |
| use modified BN instead of vanilla BN | N-Cars · accuracy | 0.867 -> 0.939 | Helped | Leveraging Asynchronous Spiking Neural Networks for Ultra Efficient Event-Based Visual Processing (AAAI 2025 · 3 citations) |
| add LA-Loss to Mem-Loss | SL-Animals · accuracy | 87.50 (+3.57) -> 88.39 (+4.46) | Helped | Spiking Neural Network as Adaptive Event Stream Slicer (NeurIPS 2024 · 3 citations) |
| Use saliency-map guidance instead of CAM guidance in EventRPG | N-Caltech101 · accuracy | 85.00 -> 85.62 | Helped | EventRPG: Event Data Augmentation with Relevance Propagation Guidance (ICLR 2024 · 2 citations) |
| use absolute-value processing instead of [0,1] normalization for relative coordinates | Daily DVS · accuracy | 96.53% -> 97.78% | Helped | SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition (ICLR 2024) |
What reviewers will expect
Datasets and baselines named in the 5 papers of this approach from 2024–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- N-Caltech101 · 3 of 5 papers
- CIFAR10-DVS · 2 of 5 papers
- N-Cars · 2 of 5 papers
- DVS128 Gesture · 2 of 5 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 10 papers; from OpenAlex and the papers' affiliations).
- Hong Kong University of Science and Technology · 2 papers
- Northeastern University · 2 papers
Use it
Download BibTeX of 13 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Training deep spiking networks (141 papers)
- Spiking transformers (87 papers)
Elsewhere in the topic
- Sparse efficient spiking sequence models (26 papers)
- Bio-inspired spiking neuron models (22 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).