mlsanityData to 7 Oct 2026

CrowdHuman: A Benchmark for Detecting Human in a Crowd

arXiv 1805.00123 ↗First posted 30 Apr 2018cs.CVcited by 283

Not on the map. Why?

Abstract (arXiv)

Human detection has witnessed impressive progress in recent years. However, the occlusion issue of detecting human in highly crowded environments is far from solved. To make matters worse, crowd scenarios are still under-represented in current human detection benchmarks. In this paper, we introduce a new dataset, called CrowdHuman, to better evaluate detectors in crowd scenarios. The CrowdHuman dataset is large, rich-annotated and contains high diversity. There are a total of 470K human instances from the train and validation subsets, and ~22.6 persons per image, with various kinds of occlusions in the dataset. Each human instance is annotated with a head bounding-box, human visible-region bounding-box and human full-body bounding-box. Baseline performance of state-of-the-art detection frameworks on CrowdHuman is presented. The cross-dataset generalization results of CrowdHuman dataset demonstrate state-of-the-art performance on previous dataset including Caltech-USA, CityPersons, and Brainwash without bells and whistles. We hope our dataset will serve as a solid baseline and help promote future research in human detection tasks.

Key facts. Cited by 283 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 33; 2022: 70; 2023: 56; 2024: 52; 2025: 45; 2026: 27.

283 papers.

Sort:

By area:

  1. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  2. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  3. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 479
  4. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  5. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  6. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
  7. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  8. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 177
  9. 2021Occluded Video Instance Segmentation: A Benchmarkcited by 154
  10. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  11. 2024VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Taskscited by 136
  12. 2023SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenescited by 130
38 more
  1. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128
  2. 2021Simple multi-dataset detectioncited by 126
  3. 2021Learning to Track with Object Permanencecited by 117
  4. 2022MeMOT: Multi-Object Tracking with Memorycited by 113
  5. 2022Global Tracking Transformerscited by 110
  6. 2024T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergycited by 94
  7. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
  8. 2022Towards Grand Unification of Object Trackingcited by 93
  9. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 86
  10. 2022SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videoscited by 80
  11. 2023Dense Distinct Query for End-to-End Object Detectioncited by 76
  12. 2024D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinementcited by 73
  13. 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 68
  14. 2021Multiple Object Tracking with Correlation Learningcited by 67
  15. 2024DEIM: DETR with Improved Matching for Fast Convergencecited by 67
  16. 2025Detect Anything via Next Point Predictioncited by 66
  17. 2021SiamMOT: Siamese Multi-Object Trackingcited by 62
  18. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  19. 2023UniHCP: A Unified Model for Human-Centric Perceptionscited by 59
  20. 2024Multiple Object Tracking as ID Predictioncited by 58
  21. 2021RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representationcited by 52
  22. 2022Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detectioncited by 48
  23. 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
  24. 2023Merlin:Empowering Multimodal LLMs with Foresight Mindscited by 46
  25. 2022Simple Cues Lead to a Strong Multi-Object Trackercited by 44
  26. 2021Tracking Pedestrian Heads in Dense Crowdcited by 42
  27. 2021TransCenter: Transformers with Dense Representations for Multiple-Object Trackingcited by 42
  28. 2023HumanBench: Towards General Human-centric Perception with Projector Assisted Pretrainingcited by 38
  29. 2022Tracking Objects as Pixel-wise Distributionscited by 36
  30. 2024Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoderscited by 36
  31. 2025YOLOE: Real-Time Seeing Anythingcited by 36
  32. 2022STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenescited by 35
  33. 2021LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Trackingcited by 34
  34. 2022BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-trainingcited by 33
  35. 2022Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Trackingcited by 33
  36. 2022NMS Strikes Backcited by 33
  37. 2023YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detectioncited by 33
  38. 2022Progressive End-to-End Object Detection in Crowded Scenescited by 31

50 most cited of 283 All 283 (JSON)