mlsanityData to 7 Oct 2026

Adaptive NMS: Refining Pedestrian Detection in a Crowd

arXiv 1904.03629 ↗First posted 7 Apr 2019cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

Pedestrian detection in a crowd is a very challenging issue. This paper addresses this problem by a novel Non-Maximum Suppression (NMS) algorithm to better refine the bounding boxes given by detectors. The contributions are threefold: (1) we propose adaptive-NMS, which applies a dynamic suppression threshold to an instance, according to the target density; (2) we design an efficient subnetwork to learn density scores, which can be conveniently embedded into both the single-stage and two-stage detectors; and (3) we achieve state of the art results on the CityPersons and CrowdHuman benchmarks.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 15; 2023: 12; 2024: 9; 2025: 9; 2026: 5.

66 papers.

Sort:

By area:

  1. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 177
  2. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  3. 2021GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detectioncited by 66
  4. 20223D Object Detection from Images for Autonomous Driving: A Surveycited by 66
  5. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 66
  6. 2021SOLO: A Simple Framework for Instance Segmentationcited by 32
  7. 2022Progressive End-to-End Object Detection in Crowded Scenescited by 31
  8. 2022Real-time Object Detection for Streaming Perceptioncited by 29
  9. 2024Relation DETR: Exploring Explicit Position Relation Prior for Object Detectioncited by 27
  10. 2023VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervisioncited by 19
  11. 2023Boosting Detection in Crowd Analysis via Underutilized Output Featurescited by 14
  12. 2024Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenescited by 13
38 more
  1. 2022You Should Look at All Objectscited by 12
  2. 2023ODAM: Gradient-based instance-specific visual explanations for object detectioncited by 12
  3. 2021Variational Pedestrian Detectioncited by 10
  4. 2023FAQ: Feature Aggregated Queries for Transformer-based Video Object Detectorscited by 10
  5. 2021BlockCopy: High-Resolution Video Processing with Block-Sparse Feature Propagation and Online Policiescited by 9
  6. 2022Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyondcited by 8
  7. 2022Beta R-CNN: Looking into Pedestrian Detection from Another Perspectivecited by 8
  8. 2021LLA: Loss-aware Label Assignment for Dense Pedestrian Detectioncited by 7
  9. 2021NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detectioncited by 7
  10. 2021Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challengecited by 6
  11. 2021Contrastive Object Detection Using Knowledge Graph Embeddingscited by 6
  12. 2022PointNeuron: 3D Neuron Reconstruction via Geometry and Topology Learning of Point Cloudscited by 6
  13. 2022Improving Crowded Object Detection via Copy-Pastecited by 6
  14. 2022Body-Part Joint Detection and Association via Extended Object Representationcited by 5
  15. 2022DEYO: DETR with YOLO for Step-by-Step Object Detectioncited by 4
  16. 2023DEYOv2: Rank Feature with Greedy Matching for End-to-End Object Detectioncited by 3
  17. 2023Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in NMScited by 3
  18. 2024Robust Pedestrian Detection via Constructing Versatile Pedestrian Knowledge Bankcited by 3
  19. 2025Multi-Cue Adaptive Visual Token Pruning for Large Vision-Language Modelscited by 3
  20. 2021V2F-Net: Explicit Decomposition of Occluded Pedestrian Detectioncited by 2
  21. 2021VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matchingcited by 2
  22. 2021PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recoverycited by 2
  23. 2021Pedestrian Detection by Exemplar-Guided Contrastive Learningcited by 2
  24. 2022IoU-Enhanced Attention for End-to-End Task Specific Object Detectioncited by 2
  25. 2023BPJDet: Extended Object Representation for Generic Body-Part Joint Detectioncited by 2
  26. 2024From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networkscited by 2
  27. 2024Accelerating Non-Maximum Suppression: A Graph Theory Perspectivecited by 2
  28. 2025IMM-MOT: A Novel 3D Multi-object Tracking Framework with Interacting Multiple Model Filtercited by 2
  29. 2025E-SAM: Training-Free Segment Every Entity Modelcited by 2
  30. 2025CMF-IoU: Multi-Stage Cross-Modal Fusion 3D Object Detection with IoU Joint Predictioncited by 2
  31. 2021You Better Look Twice: a new perspective for designing accurate detectors with reduced computationscited by 1
  32. 2023Do We Still Need Non-Maximum Suppression? Accurate Confidence Estimates and Implicit Duplication Modeling with IoU-Aware Calibrationcited by 1
  33. 2024PBADet: A One-Stage Anchor-Free Approach for Part-Body Associationcited by 1
  34. 2024Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completioncited by 1
  35. 2024SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Drivingcited by 1
  36. 2025Work-Efficient Parallel Non-Maximum Suppression Kernelscited by 1
  37. 2025Density-based Object Detection in Crowded Scenescited by 1
  38. 2025CrowdQuery: Density-Guided Query Module for Enhanced 2D and 3D Detection in Crowded Scenescited by 1

50 most cited of 66 All 66 (JSON)