Research map / Detection and segmentation / CNN features
Spiking event-camera detection
Detect objects from event data using spiking and hybrid neural networks.
40 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2018–2026) · an approach in CNN features, keyword cluster “text · event · scene”
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.
8 papers in 2023–24 and 25 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic grew, from 2.4% to 7.2%.
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
- 2018 · HATS: Histograms of Averaged Time Surfaces for Robust Event-Based Object Classification (CVPR 2018 · 498 citations)
- 2019 · Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras (CVPR 2019 · 106 citations)
- 2020 · Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection (AAAI 2020 · 436 citations)
- 2021 · SoundDet: Polyphonic Moving Sound Event Detection and Localization from Raw Waveform (ICML 2021 · 10 citations)
- 2022 · Event-Image Fusion Stereo Using Cross-Modality Feature Propagation (AAAI 2022 · 25 citations)
- 2023 · Recurrent Vision Transformers for Object Detection With Event Cameras (CVPR 2023 · 202 citations)
- 2024 · Scene Adaptive Sparse Transformer for Event-based Object Detection (CVPR 2024 · 37 citations)
- 2025 · Brain-Inspired Spiking Neural Networks for Energy-Efficient Object Detection (CVPR 2025 · 15 citations)
- 2026 · PEOD: A Pixel-Aligned Event-RGB Benchmark for Object Detection Under Challenging Conditions (AAAI 2026 · 3 citations)
Earliest papers here
- HATS: Histograms of Averaged Time Surfaces for Robust Event-Based Object Classification (CVPR 2018 · 498 citations)
- Speed Invariant Time Surface for Learning to Detect Corner Points With Event-Based Cameras (CVPR 2019 · 106 citations)
- Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detection (AAAI 2020 · 436 citations)
What has been tried
27 papers here report 287 measured changes (a component added, removed or swapped, compared with a baseline): helped 80%, no clear effect 3%, hurt 16%, mixed 1%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| Add context broadcasting to SAST | 1Mpx · mAP (%) | 48.3 -> 48.7 | Helped | Scene Adaptive Sparse Transformer for Event-based Object Detection (CVPR 2024 · 37 citations) |
| Use Spiking Rate Decoding instead of Spiking Count Decoding | NCAR · accuracy | 0.869 -> 0.937 | Helped | SFOD: Spiking Fusion Object Detector (CVPR 2024 · 20 citations) |
| Add ONNB to the baseline | Gen1 · mAP@0.5 | 56.8 -> 64.3 | Helped | Brain-Inspired Spiking Neural Networks for Energy-Efficient Object Detection (CVPR 2025 · 15 citations) |
| add IoU-based query selection | EvDET200K · mAP | 40.9 -> 41.6 | Helped | Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset (CVPR 2025 · 15 citations) |
| add the STCA spatiotemporal-continuity scoring method instead of variance, entropy, or a learnable scoring module | eTram · mAP | 30.8, 30.4, 31.2 -> 32.6 | Helped | SMamba: Sparse Mamba for Event-based Object Detection (AAAI 2025 · 14 citations) |
| Add CFDL while retaining a fixed 1×1 convolutional detector | HVGA ATIS Corner (25ms) · reprojection error (pixels) | 5.45 -> 1.13 | Helped | SD2Event:Self-supervised Learning of Dynamic Detectors and Contextual Descriptors for Event Cameras (CVPR 2024 · 11 citations) |
| add temporal attention Φta | Gen1 Automotive Detection · mAP | 0.33 -> 0.35 | Helped | Efficient Event-Based Object Detection: A Hybrid Neural Network with Spatial and Temporal Attention (CVPR 2025 · 10 citations) |
| Add concatenation fusion instead of no fusion | DSEC · mIoU | 54.19 -> 54.48 | Helped | ESEG: Event-Based Segmentation Boosted by Explicit Edge-Semantic Guidance (AAAI 2025 · 7 citations) |
| replace FSN-BP with CLR | NCARs · accuracy | 0.948 -> 0.952 | Helped | CREST: An Efficient Conjointly-trained Spike-driven Framework for Event-based Object Detection Exploiting Spatiotemporal Dynamics (AAAI 2025 · 5 citations) |
| add AWT to the frame-event baseline | DSEC-Semantic · mIoU | 61.06 -> 63.59 | Helped | Efficient Event-Based Semantic Segmentation via Exploiting Frame-Event Fusion: A Hybrid Neural Network Approach (AAAI 2025 · 4 citations) |
| use ternary signed spiking neurons instead of IF neurons | COCO2017 val · mAP | 56.85 -> 56.97 | Helped | SpikingYOLOX: Improved YOLOX Object Detection with Fast Fourier Convolution and Spiking Neural Networks (AAAI 2025 · 3 citations) |
| adaptively activate TAC using SSM instead of keeping TAC inactive | Gen1 · mAP@0.5:0.95 | 42.1 -> 49.6 | Helped | EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection (NeurIPS 2024 · 2 citations) |
What reviewers will expect
Datasets and baselines named in the 15 papers of this approach from 2025–2026 that have a full-text summary. Leaving out the common ones is a frequent review question.
Datasets
- Gen1 · 5 of 15 papers
- DSEC-Semantic · 2 of 15 papers
- 1Mpx · 2 of 15 papers
Baselines
- RVT · 4 of 15 papers
- RED · 3 of 15 papers
- SAST · 3 of 15 papers
- SFOD · 2 of 15 papers
- Ev-SegNet · 2 of 15 papers
- EvSegFormer · 2 of 15 papers
- ESS-Sup · 2 of 15 papers
- ESS · 2 of 15 papers
Recent preprints
Loading recent arXiv preprints…
Who publishes on it
Institutions on the most papers of this approach since 2023 (of 33 papers; from OpenAlex and the papers' affiliations).
- University of Science and Technology of China · 4 papers
- Dalian University of Technology · 4 papers
- Zhejiang University · 3 papers
- Institute of Artificial Intelligence · 2 papers
- Chang’an University · 2 papers
- Anhui University · 2 papers
- Beijing Institute of Technology · 2 papers
- Peking University · 2 papers
Use it
Download BibTeX of 31 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
- Arbitrary-shape scene text detection (61 papers)
Elsewhere in the topic
- Context modeling for semantic segmentation (241 papers)
- Region-based and query-based detectors (183 papers)
- Local features and context in CNNs (170 papers)
- Context for hard detection conditions (133 papers)
- Domain-specific segmentation and detection (118 papers)
- Convolution-transformer backbones (101 papers)
- Box regression and loss design (94 papers)
- Efficient DETR query design (85 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).