Papers › CrowdHuman: A Benchmark for Detecting Human in a Crowd

CrowdHuman: A Benchmark for Detecting Human in a Crowd

30 Apr 2018arXiv:1805.00123archive 2025-07-28

Shuai Shao, Zijian Zhao, Boxun Li, Tete Xiao, Gang Yu, Xiangyu Zhang, Jian Sun

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.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

aibeedetect/bfjdet mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CVF open access id Wan_Body-Face_Joint_Detection_via_Embedding_and_Head_Hook_ICCV_2021_paper (that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityHuman DetectionObject DetectionPedestrian Detection

Datasets

Introduced by this paper, per the archive.

CrowdHuman

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Detection CrowdHuman (full body) Faster RCNN (ResNet50) AP 84.95 #17 of 19 Archive leaderboard report
Object Detection CrowdHuman (full body) Faster RCNN (ResNet50) mMR 50.49 #17 of 19 Archive leaderboard report
Pedestrian Detection Caltech FRCNN+FPN-Res50+refined feature map+Crowdhuman Reasonable Miss Rate 3.46 #7 of 33 Archive leaderboard report
Pedestrian Detection CityPersons FRCNN+FPN-Res50+refined feature map+Crowdhuman Reasonable MR^-2 10.67 #12 of 22 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections