# NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing

arXiv: https://arxiv.org/abs/2003.12729 · HTML: https://mlsanity.com/paper/2003.12729/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2020.

## Built on by (most cited first, 30 of 36)

- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [DocSegTr: An Instance-Level End-to-End Document Image Segmentation Transformer](https://mlsanity.com/paper/2201.11438/) (2022)
- [VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision](https://mlsanity.com/paper/2304.03135/) (2023)
- [TFDet: Target-Aware Fusion for RGB-T Pedestrian Detection](https://mlsanity.com/paper/2305.16580/) (2023)
- [Towards Real-time High-Definition Image Snow Removal: Efficient Pyramid Network with Asymmetrical Encoder-decoder Architecture](https://mlsanity.com/paper/2207.05605/) (2022)
- [Beta R-CNN: Looking into Pedestrian Detection from Another Perspective](https://mlsanity.com/paper/2210.12758/) (2022)
- [LLA: Loss-aware Label Assignment for Dense Pedestrian Detection](https://mlsanity.com/paper/2101.04307/) (2021)
- [NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection](https://mlsanity.com/paper/2106.02426/) (2021)
- [Detecting and Matching Related Objects with One Proposal Multiple Predictions](https://mlsanity.com/paper/2104.12574/) (2021)
- [Box Re-Ranking: Unsupervised False Positive Suppression for Domain Adaptive Pedestrian Detection](https://mlsanity.com/paper/2102.00595/) (2021)
- [IoU-Enhanced Attention for End-to-End Task Specific Object Detection](https://mlsanity.com/paper/2209.10391/) (2022)
- [Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detection](https://mlsanity.com/paper/2305.10801/) (2023)
- [Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in NMS](https://mlsanity.com/paper/2310.13951/) (2023)
- [Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bank](https://mlsanity.com/paper/2404.19299/) (2024)
- [V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection](https://mlsanity.com/paper/2104.03106/) (2021)
- [Pedestrian Detection by Exemplar-Guided Contrastive Learning](https://mlsanity.com/paper/2111.08974/) (2021)
- [RefCrowd: Grounding the Target in Crowd with Referring Expressions](https://mlsanity.com/paper/2206.08172/) (2022)
- [BPJDet: Extended Object Representation for Generic Body-Part Joint Detection](https://mlsanity.com/paper/2304.10765/) (2023)
- [Nighttime Pedestrian Detection Based on Fore-Background Contrast Learning](https://mlsanity.com/paper/2408.03030/) (2024)
- [Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detection](https://mlsanity.com/paper/2505.16029/) (2025)
- [Real-time Human-Centric Segmentation for Complex Video Scenes](https://mlsanity.com/paper/2108.07199/) (2021)
- [Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patches](https://mlsanity.com/paper/2311.06122/) (2023)
- [PBADet: A One-Stage Anchor-Free Approach for Part-Body Association](https://mlsanity.com/paper/2402.07814/) (2024)
- [Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion](https://mlsanity.com/paper/2405.01311/) (2024)
- [Density-based Object Detection in Crowded Scenes](https://mlsanity.com/paper/2504.09819/) (2025)
- [A Full-Stage Refined Proposal Algorithm for Suppressing False Positives in Two-Stage CNN-Based Detection Methods](https://mlsanity.com/paper/2508.01382/) (2025)
- [Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection](https://mlsanity.com/paper/2103.10091/) (2021)
- [Segmentation-Based Bounding Box Generation for Omnidirectional Pedestrian Detection](https://mlsanity.com/paper/2104.13764/) (2021)
- [TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detection](https://mlsanity.com/paper/2211.00826/) (2022)

## Abstract (arXiv)

Although significant progress has been made in pedestrian detection recently, pedestrian detection in crowded scenes is still challenging. The heavy occlusion between pedestrians imposes great challenges to the standard Non-Maximum Suppression (NMS). A relative low threshold of intersection over union (IoU) leads to missing highly overlapped pedestrians, while a higher one brings in plenty of false positives. To avoid such a dilemma, this paper proposes a novel Representative Region NMS approach leveraging the less occluded visible parts, effectively removing the redundant boxes without bringing in many false positives. To acquire the visible parts, a novel Paired-Box Model (PBM) is proposed to simultaneously predict the full and visible boxes of a pedestrian. The full and visible boxes constitute a pair serving as the sample unit of the model, thus guaranteeing a strong correspondence between the two boxes throughout the detection pipeline. Moreover, convenient feature integration of the two boxes is allowed for the better performance on both full and visible pedestrian detection tasks. Experiments on the challenging CrowdHuman and CityPersons benchmarks sufficiently validate the effectiveness of the proposed approach on pedestrian detection in the crowded situation.