# Detection in Crowded Scenes: One Proposal, Multiple Predictions

arXiv: https://arxiv.org/abs/2003.09163 · HTML: https://mlsanity.com/paper/2003.09163/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2020.

## Built on by (most cited first, 30 of 59)

- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space](https://mlsanity.com/paper/2309.14616/) (2023)
- [QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking](https://mlsanity.com/paper/2210.06984/) (2022)
- [4D-Net for Learned Multi-Modal Alignment](https://mlsanity.com/paper/2109.01066/) (2021)
- [HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining](https://mlsanity.com/paper/2303.05675/) (2023)
- [Progressive End-to-End Object Detection in Crowded Scenes](https://mlsanity.com/paper/2203.07669/) (2022)
- [Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation](https://mlsanity.com/paper/2101.11223/) (2021)
- [Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection](https://mlsanity.com/paper/2109.03426/) (2021)
- [Hulk: A Universal Knowledge Translator for Human-Centric Tasks](https://mlsanity.com/paper/2312.01697/) (2023)
- [Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generation](https://mlsanity.com/paper/2507.08441/) (2025)
- [Relieving Long-tailed Instance Segmentation via Pairwise Class Balance](https://mlsanity.com/paper/2201.02784/) (2022)
- [Exploring Visual Context for Weakly Supervised Person Search](https://mlsanity.com/paper/2106.10506/) (2021)
- [Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimation](https://mlsanity.com/paper/2201.01297/) (2022)
- [Towards Domain Generalization in Object Detection](https://mlsanity.com/paper/2203.14387/) (2022)
- [Prediction-Guided Distillation for Dense Object Detection](https://mlsanity.com/paper/2203.05469/) (2022)
- [ODAM: Gradient-based instance-specific visual explanations for object detection](https://mlsanity.com/paper/2304.06354/) (2023)
- [Variational Pedestrian Detection](https://mlsanity.com/paper/2104.12389/) (2021)
- [When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset](https://mlsanity.com/paper/2407.10125/) (2024)
- [Beta R-CNN: Looking into Pedestrian Detection from Another Perspective](https://mlsanity.com/paper/2210.12758/) (2022)
- [Consistency-Aware Anchor Pyramid Network for Crowd Localization](https://mlsanity.com/paper/2212.04067/) (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)
- [NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistency](https://mlsanity.com/paper/2306.16661/) (2023)
- [Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge](https://mlsanity.com/paper/2111.07950/) (2021)
- [Improving Crowded Object Detection via Copy-Paste](https://mlsanity.com/paper/2211.12110/) (2022)
- [CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRs](https://mlsanity.com/paper/2502.10683/) (2025)
- [Body-Part Joint Detection and Association via Extended Object Representation](https://mlsanity.com/paper/2212.07652/) (2022)
- [Robust Backdoor Attacks on Object Detection in Real World](https://mlsanity.com/paper/2309.08953/) (2023)
- [Detecting and Matching Related Objects with One Proposal Multiple Predictions](https://mlsanity.com/paper/2104.12574/) (2021)
- [Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Images](https://mlsanity.com/paper/2109.03451/) (2021)

## Abstract (arXiv)

We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes. The key of our approach is to let each proposal predict a set of correlated instances rather than a single one in previous proposal-based frameworks. Equipped with new techniques such as EMD Loss and Set NMS, our detector can effectively handle the difficulty of detecting highly overlapped objects. On a FPN-Res50 baseline, our detector can obtain 4.9% AP gains on challenging CrowdHuman dataset and 1.0% MR-2 improvements on CityPersons dataset, without bells and whistles. Moreover, on less crowed datasets like COCO, our approach can still achieve moderate improvement, suggesting the proposed method is robust to crowdedness. Code and pre-trained models will be released at https://github.com/megvii-model/CrowdDetection.