mlsanityData to 14 Oct 2026

Detection in Crowded Scenes: One Proposal, Multiple Predictions

arXiv 2003.09163 ↗First posted 20 Mar 2020cs.CVcited by 59

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 15; 2022: 12; 2023: 13; 2024: 4; 2025: 10; 2026: 5.

59 papers.

Sort:

By area:

  1. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  2. 2023NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Spacecited by 90
  3. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  4. 20214D-Net for Learned Multi-Modal Alignmentcited by 44
  5. 2023HumanBench: Towards General Human-centric Perception with Projector Assisted Pretrainingcited by 38
  6. 2022Progressive End-to-End Object Detection in Crowded Scenescited by 31
  7. 2021Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimationcited by 30
  8. 2021Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detectioncited by 23
  9. 2023Hulk: A Universal Knowledge Translator for Human-Centric Taskscited by 22
  10. 2025Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Image Generationcited by 21
  11. 2022Relieving Long-tailed Instance Segmentation via Pairwise Class Balancecited by 18
  12. 2021Exploring Visual Context for Weakly Supervised Person Searchcited by 16
38 more
  1. 2022Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimationcited by 16
  2. 2022Towards Domain Generalization in Object Detectioncited by 16
  3. 2022Prediction-Guided Distillation for Dense Object Detectioncited by 14
  4. 2023ODAM: Gradient-based instance-specific visual explanations for object detectioncited by 12
  5. 2021Variational Pedestrian Detectioncited by 10
  6. 2024When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Datasetcited by 10
  7. 2022Beta R-CNN: Looking into Pedestrian Detection from Another Perspectivecited by 8
  8. 2022Consistency-Aware Anchor Pyramid Network for Crowd Localizationcited by 8
  9. 2021LLA: Loss-aware Label Assignment for Dense Pedestrian Detectioncited by 7
  10. 2021NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detectioncited by 7
  11. 2023NaturalInversion: Data-Free Image Synthesis Improving Real-World Consistencycited by 7
  12. 2021Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challengecited by 6
  13. 2022Improving Crowded Object Detection via Copy-Pastecited by 6
  14. 2025CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRscited by 6
  15. 2022Body-Part Joint Detection and Association via Extended Object Representationcited by 5
  16. 2023Robust Backdoor Attacks on Object Detection in Real Worldcited by 5
  17. 2021Detecting and Matching Related Objects with One Proposal Multiple Predictionscited by 4
  18. 2021Which and Where to Focus: A Simple yet Accurate Framework for Arbitrary-Shaped Nearby Text Detection in Scene Imagescited by 4
  19. 2023ECEA: Extensible Co-Existing Attention for Few-Shot Object Detectioncited by 4
  20. 2023Selecting Learnable Training Samples is All DETRs Need in Crowded Pedestrian Detectioncited by 3
  21. 2025YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multibranch Feature Interactioncited by 3
  22. 2021V2F-Net: Explicit Decomposition of Occluded Pedestrian Detectioncited by 2
  23. 2021Pedestrian Detection by Exemplar-Guided Contrastive Learningcited by 2
  24. 2022Multiview Detection with Cardboard Human Modelingcited by 2
  25. 2023Handling Heavy Occlusion in Dense Crowd Tracking by Focusing on the Headscited by 2
  26. 2023BPJDet: Extended Object Representation for Generic Body-Part Joint Detectioncited by 2
  27. 2023ICON2: Reliably Benchmarking Predictive Inequity in Object Detectioncited by 2
  28. 2024Nighttime Pedestrian Detection Based on Fore-Background Contrast Learningcited by 2
  29. 2025Scale-Aware Pre-Training for Human-Centric Visual Perception: Enabling Lightweight and Generalizable Modelscited by 2
  30. 2025Learning better representations for crowded pedestrians in offboard LiDAR-camera 3D tracking-by-detectioncited by 2
  31. 2024PBADet: A One-Stage Anchor-Free Approach for Part-Body Associationcited by 1
  32. 2024Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completioncited by 1
  33. 2025Density-based Object Detection in Crowded Scenescited by 1
  34. 2025CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenescited by 1
  35. 2026Vision Foundation Models as Generalist Tokenizers for Image Generationcited by 1
  36. 2021Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detectioncited by 0
  37. 2021MPSN: Motion-aware Pseudo Siamese Network for Indoor Video Head Detection in Buildingscited by 0
  38. 2022TSAA: A Two-Stage Anchor Assignment Method towards Anchor Drift in Crowded Object Detectioncited by 0

50 most cited of 59 All 59 (JSON)