Research map / Detection and segmentation / CNN features
Learning to Detect Objects with a 1 Megapixel Event Camera
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add recurrent internal memory to the detector (ablation) | RED · 1Mpx Detection Dataset | mAP: 0.29 -> 0.43 | Helped |
| Add recurrent internal memory to the detector (ablation) | RED · 1Mpx Detection Dataset | mAP75: 0.26 -> 0.44 | Helped |
| Add temporal consistency loss (ablation) | RED with Event Volume input · 1Mpx Detection Dataset | mAP: 0.41 -> 0.43 | Helped |
| Add temporal consistency loss (ablation) | RED with Event Volume input · 1Mpx Detection Dataset | mAP75: 0.40 -> 0.44 | Helped |
| Replace Histogram input with Time Surface input (ablation) | RED · 1Mpx Detection Dataset | mAP: 0.37 -> 0.39 | Helped |
| Replace Time Surface input with Event Volume input (ablation) | RED · 1Mpx Detection Dataset | mAP: 0.39 -> 0.41 | Helped |
| Use recurrent event processing instead of feed-forward event detection | RED versus Events-RetinaNet · 1Mpx Detection Dataset | mAP: 0.18 -> 0.43 | Helped |
| Detect directly from events instead of reconstructing intensity images first | RED versus E2Vid-RetinaNet · 1Mpx Detection Dataset | mAP: 0.25 -> 0.43 | Helped |
| Detect directly from events instead of reconstructing intensity images first | RED versus E2Vid-RetinaNet · 1Mpx Detection Dataset | runtime (ms): 840.66 -> 39.33 | Helped |
| Use event input rather than grayscale images | RED versus Gray-RetinaNet · 1Mpx Detection Dataset | mAP: 0.43 vs 0.43 | No clear effect |
| Use event input rather than grayscale images | RED versus Gray-RetinaNet · Gen1 Detection Dataset | mAP: 0.44 -> 0.40 | Hurt |
Closest papers by meaning
- FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies (NeurIPS 2025 · similarity 0.90)
- LEOD: Label-Efficient Object Detection for Event Cameras (CVPR 2024 · similarity 0.89)
- Object Detection using Event Camera: A MoE Heat Conduction based Detector and A New Benchmark Dataset (CVPR 2025 · similarity 0.89)
- PASS: Path-selective State Space Model for Event-based Recognition (NeurIPS 2025 · similarity 0.88)
- Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline (CVPR 2024 · similarity 0.88)
- EventPillars: Pillar-based Efficient Representations for Event Data (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.