Research map / Detection and segmentation / Open-set and few-shot detection
MixedPeds: Pedestrian Detection in Unannotated Videos Using Synthetically Generated Human-Agents for Training
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 |
|---|---|---|---|
| Train with MixedPeds synthetic data rather than the combined-dataset baseline | Faster R-CNN pedestrian detector · CALTECH | average precision: 17.5% -> 25.3% | Helped |
| Train with MixedPeds synthetic data rather than the combined-dataset baseline | Faster R-CNN pedestrian detector · KITTI | average precision: 44.0% -> 49.0% | Helped |
| Train with MixedPeds synthetic data rather than the combined-dataset baseline | Faster R-CNN pedestrian detector · ETHZ | average precision: 39.3% -> 53.0% | Helped |
| Add the rendering techniques (ablation) | MixedPeds · CALTECH | average precision: 22.1% -> 25.3% | Helped |
| Add the rendering techniques (ablation) | MixedPeds · KITTI | average precision: 45.4% -> 49.0% | Helped |
| Add the rendering techniques (ablation) | MixedPeds · ETHZ | average precision: 48.3% -> 53.0% | Helped |
| Add initial clustering when producing the Spawn Probability Maps (ablation) | MixedPeds · CALTECH | average precision: 17.9% -> 25.3% | Helped |
| Add initial clustering when producing the Spawn Probability Maps (ablation) | MixedPeds · KITTI | average precision: 46.1% -> 49.0% | Helped |
| Add initial clustering when producing the Spawn Probability Maps (ablation) | MixedPeds · ETHZ | average precision: 51.3% -> 53.0% | Helped |
| Use Spawn Probability Maps instead of random pedestrian placement (ablation) | MixedPeds · CALTECH | average precision: 15.4% -> 25.3% | Helped |
| Use Spawn Probability Maps instead of random pedestrian placement (ablation) | MixedPeds · KITTI | average precision: 31.0% -> 49.0% | Helped |
| Use Spawn Probability Maps instead of random pedestrian placement (ablation) | MixedPeds · ETHZ | average precision: 43.9% -> 53.0% | Helped |
Closest papers by meaning
- Expecting the Unexpected: Training Detectors for Unusual Pedestrians With Adversarial Imposters (CVPR 2017 · similarity 0.90)
- How Far Are We From Solving Pedestrian Detection? (CVPR 2016 · similarity 0.89)
- Community Forensics: Using Thousands of Generators to Train Fake Image Detectors (CVPR 2025 · similarity 0.86)
- HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes (CVPR 2024 · similarity 0.85)
- Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels (ICLR 2025 · similarity 0.85)
- Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset (AAAI 2025 · similarity 0.84)
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.