# CrowdHuman: A Benchmark for Detecting Human in a Crowd

arXiv: https://arxiv.org/abs/1805.00123 · HTML: https://mlsanity.com/paper/1805.00123/

## Key facts

- Cited by 284 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2018.

## Built on by (most cited first, 30 of 284)

- [ByteTrack: Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2110.06864/) (2021)
- [TrackFormer: Multi-Object Tracking with Transformers](https://mlsanity.com/paper/2101.02702/) (2021)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [MOTR: End-to-End Multiple-Object Tracking with Transformer](https://mlsanity.com/paper/2105.03247/) (2021)
- [DiffusionDet: Diffusion Model for Object Detection](https://mlsanity.com/paper/2211.09788/) (2022)
- [BoT-SORT: Robust Associations Multi-Pedestrian Tracking](https://mlsanity.com/paper/2206.14651/) (2022)
- [StrongSORT: Make DeepSORT Great Again](https://mlsanity.com/paper/2202.13514/) (2022)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors](https://mlsanity.com/paper/2211.09791/) (2022)
- [VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks](https://mlsanity.com/paper/2406.08394/) (2024)
- [SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes](https://mlsanity.com/paper/2304.05170/) (2023)
- [Efficient DETR: Improving End-to-End Object Detector with Dense Prior](https://mlsanity.com/paper/2104.01318/) (2021)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Learning to Track with Object Permanence](https://mlsanity.com/paper/2103.14258/) (2021)
- [MeMOT: Multi-Object Tracking with Memory](https://mlsanity.com/paper/2203.16761/) (2022)
- [Global Tracking Transformers](https://mlsanity.com/paper/2203.13250/) (2022)
- [T-Rex2: Towards Generic Object Detection via Text-Visual Prompt Synergy](https://mlsanity.com/paper/2403.14610/) (2024)
- [TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Tracking](https://mlsanity.com/paper/2104.00194/) (2021)
- [Towards Grand Unification of Object Tracking](https://mlsanity.com/paper/2207.07078/) (2022)
- [MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking](https://mlsanity.com/paper/2307.15700/) (2023)
- [SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videos](https://mlsanity.com/paper/2204.06918/) (2022)
- [Dense Distinct Query for End-to-End Object Detection](https://mlsanity.com/paper/2303.12776/) (2023)
- [D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement](https://mlsanity.com/paper/2410.13842/) (2024)
- [Detect Anything via Next Point Prediction](https://mlsanity.com/paper/2510.12798/) (2025)
- [MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?](https://mlsanity.com/paper/2108.09518/) (2021)
- [DEIM: DETR with Improved Matching for Fast Convergence](https://mlsanity.com/paper/2412.04234/) (2024)
- [Multiple Object Tracking with Correlation Learning](https://mlsanity.com/paper/2104.03541/) (2021)
- [SiamMOT: Siamese Multi-Object Tracking](https://mlsanity.com/paper/2105.11595/) (2021)
- [QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking](https://mlsanity.com/paper/2210.06984/) (2022)

## 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.