{"url":"/dataset/crowdhuman","name":"CrowdHuman","full_name":null,"description_markdown":"**CrowdHuman** is a large and rich-annotated human detection dataset, which contains 15,000, 4,370 and 5,000 images collected from the Internet for training, validation and testing respectively. The number is more than 10× boosted compared with previous challenging pedestrian detection dataset like CityPersons. The total number of persons is also noticeably larger than the others with ∼340k person and ∼99k ignore region annotations in the CrowdHuman training subset.\r\n\r\nSource: [SADet: Learning An Efficient and Accurate Pedestrian Detector](https://arxiv.org/abs/2007.13119)\r\nImage Source: [http://www.crowdhuman.org/](http://www.crowdhuman.org/)","description_withheld":null,"homepage":"http://www.crowdhuman.org/","introduced_date":"2018-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/crowdhuman-a-benchmark-for-detecting-human-in","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","first_author":"Shuai Shao","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"}],"languages":[],"variants":["CrowdHuman (full body)","CrowdHuman"],"data_loaders":[],"num_papers_in_archive":161,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/object-detection-on-crowdhuman-full-body","task":"Object Detection","dataset_variant":"CrowdHuman (full body)","rows":19,"metrics":["AP","mMR","Recall"],"first_row_in_archive_order":{"model":"InternImage-H","paper":"/paper/internimage-exploring-large-scale-vision","metrics":{"AP":"97.2"},"code_links":[{"title":"opengvlab/internimage","url":"https://github.com/opengvlab/internimage"},{"title":"OpenGVLab/M3I-Pretraining","url":"https://github.com/OpenGVLab/M3I-Pretraining"},{"title":"chenller/mmseg-extension","url":"https://github.com/chenller/mmseg-extension"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/object-detection-on-crowdhuman","task":"Object Detection","dataset_variant":"CrowdHuman","rows":1,"metrics":["AP","MR^-2"],"first_row_in_archive_order":{"model":"S-RCNN+Ours","paper":"/paper/progressive-end-to-end-object-detection-in","metrics":{"AP":"92.5","MR^-2":"41.4"},"code_links":[{"title":"megvii-model/iter-e2edet","url":"https://github.com/megvii-model/iter-e2edet"},{"title":"zyayoung/Iter-Deformable-DETR","url":"https://github.com/zyayoung/Iter-Deformable-DETR"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/when-pedestrian-detection-meets-multi-modal","title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","date":"2024-07-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hulk-a-universal-knowledge-translator-for","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","date":"2023-12-04","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":12,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dense-distinct-query-for-end-to-end-object","title":"Dense Distinct Query for End-to-End Object Detection","date":"2023-03-22","rows_on_this_dataset":3,"code_links":2,"syntology":null},{"paper":"/paper/unihcp-a-unified-model-for-human-centric","title":"UniHCP: A Unified Model for Human-Centric Perceptions","date":"2023-03-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":13,"samples_ran":7,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/internimage-exploring-large-scale-vision","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","date":"2022-11-10","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":2,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/beta-r-cnn-looking-into-pedestrian-detection-1","title":"Beta R-CNN: Looking into Pedestrian Detection from Another Perspective","date":"2022-10-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/progressive-end-to-end-object-detection-in","title":"Progressive End-to-End Object Detection in Crowded Scenes","date":"2022-03-15","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/v2f-net-explicit-decomposition-of-occluded","title":"V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection","date":"2021-04-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/noh-nms-improving-pedestrian-detection-by","title":"NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination","date":"2020-07-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/iterdet-iterative-scheme-for-objectdetection","title":"IterDet: Iterative Scheme for Object Detection in Crowded Environments","date":"2020-05-12","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/detection-in-crowded-scenes-one-proposal","title":"Detection in Crowded Scenes: One Proposal, Multiple Predictions","date":"2020-03-20","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":10,"samples_ran":0,"samples_unverified":10,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ps-rcnn-detecting-secondary-human-instances","title":"PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression","date":"2020-03-16","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/adaptive-nms-refining-pedestrian-detection-in","title":"Adaptive NMS: Refining Pedestrian Detection in a Crowd","date":"2019-04-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/crowdhuman-a-benchmark-for-detecting-human-in","title":"CrowdHuman: A Benchmark for Detecting Human in a Crowd","date":"2018-04-30","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":5,"samples_harvested":52,"samples_ran":22,"samples_unverified":30,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":1,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}