| Increasing pedestrian detection performance through weighting of detection impairing factors | | 6.23 | 28.37 | | | 7.36 | | | | DIW Loss | 2022-12-08 |
| Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving | | 6.38 | 24.73 | | | 7.90 | | | 0.18 | LSFM (Additional Data) | 2023-01-01 |
| Generalizable Pedestrian Detection: The Elephant In The Room | ✓ Link | 7.5 | 33.9 | 5.7 | 6.2 | 8.0 | 3.0 | 4.3 | | Pedestron | 2020-03-19 |
| F2DNet: Fast Focal Detection Network for Pedestrian Detection | ✓ Link | 7.8 | 26.23 | | | 9.43 | | | 0.44s/img | F2DNet (extra data) | 2022-03-04 |
| Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving | | 8.5 | 31.9 | | | 8.8 | | | 0.18 | LSFM | 2023-01-01 |
| F2DNet: Fast Focal Detection Network for Pedestrian Detection | ✓ Link | 8.7 | 32.6 | | | 11.3 | | | 0.44s/img | F2DNet | 2022-03-04 |
| Adapted Center and Scale Prediction: More Stable and More Accurate | ✓ Link | 9.3 | 46.3 | 8.7 | 5.6 | | | | | ACSP | 2020-02-20 |
| VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision | ✓ Link | 9.4 | 43.1 | 8.8 | 6.1 | 10.9 | | | | VLPD | 2023-04-06 |
| Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks | ✓ Link | 9.7 | 39.4 | | | | | | | SOLIDER | 2023-03-30 |
| NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection | ✓ Link | 10.08 | | | | | | | | NMS-Loss | 2021-06-04 |
| Beta R-CNN: Looking into Pedestrian Detection from Another Perspective | | 10.6 | 47.1 | 10.3 | 6.4 | | | | | Beta R-CNN | 2022-10-23 |
| CrowdHuman: A Benchmark for Detecting Human in a Crowd | ✓ Link | 10.67 | | | | | | | | FRCNN+FPN-Res50+refined feature map+Crowdhuman | 2018-04-30 |
| NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination | ✓ Link | 10.8 | 53.0 | 11.2 | 6.6 | | | | | NOH-NMS | 2020-07-27 |
| Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection | ✓ Link | 11.0 | 49.3 | 10.4 | 7.3 | 16.0 | 3.7 | 6.5 | 0.33s/img | CSP (with offset) + ResNet-50 | 2019-04-05 |
| Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting | ✓ Link | 12.0 | 51.9 | 11.4 | 8.4 | 19.0 | 5.7 | 6.6 | 0.27 | ALFNet | 2018-09-01 |
| Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd | | 12.8 | 55.7 | 15.3 | 6.7 | | | | | OR-CNN | 2018-07-23 |
| Repulsion Loss: Detecting Pedestrians in a Crowd | ✓ Link | 13.2 | 56.9 | 16.8 | 7.6 | | | | | RepLoss | 2017-11-21 |
| Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation | | 14.4 | 52.0 | 15.9 | 9.2 | | | | | TLL+MRF | 2018-07-04 |
| CityPersons: A Diverse Dataset for Pedestrian Detection | ✓ Link | 14.8 | | | | 22.6 | 6.7 | 8.0 | | FRCNN+Seg | 2017-02-19 |
| CityPersons: A Diverse Dataset for Pedestrian Detection | ✓ Link | 15.4 | | | | 25.6 | 7.2 | 7.9 | | FRCNN | 2017-02-19 |
| Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation | | 15.5 | 53.6 | 17.2 | 10.0 | | | | | TLL | 2018-07-04 |
| Adapted Center and Scale Prediction: More Stable and More Accurate | ✓ Link | | 42.5 | 6.9 | 4.9 | | | | | ACSP + EuroCity Persons | 2020-02-20 |