{"url":"/dataset/citypersons","name":"CityPersons","full_name":null,"description_markdown":"The **CityPersons** dataset is a subset of Cityscapes which only consists of person annotations. There are 2975 images for training, 500 and 1575 images for validation and testing. The average of the number of pedestrians in an image is 7. The visible-region and full-body annotations are provided.\r\n\r\nSource: [NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing](https://arxiv.org/abs/2003.12729)\r\nImage Source: [https://github.com/CharlesShang/Detectron-PYTORCH/tree/master/data/citypersons](https://github.com/CharlesShang/Detectron-PYTORCH/tree/master/data/citypersons)","description_withheld":null,"homepage":"https://github.com/CharlesShang/Detectron-PYTORCH/tree/master/data/citypersons","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/citypersons-a-diverse-dataset-for-pedestrian","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","first_author":"Shanshan Zhang","url":null},"license":{"name":"Custom (non-commercial)","url":"https://www.cityscapes-dataset.com/license/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Pedestrian Detection","url":"/task/pedestrian-detection","datasets_with_task":"/datasets/task/pedestrian-detection"}],"languages":[],"variants":["CityPersons"],"data_loaders":[{"repo":"https://github.com/CharlesShang/Detectron-PYTORCH","url":"https://github.com/CharlesShang/Detectron-PYTORCH","frameworks":[]}],"num_papers_in_archive":129,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/pedestrian-detection-on-citypersons","task":"Pedestrian Detection","dataset_variant":"CityPersons","rows":22,"metrics":["Reasonable MR^-2","Heavy MR^-2","Partial MR^-2","Bare MR^-2","Small MR^-2","Medium MR^-2","Large MR^-2","Test Time"],"first_row_in_archive_order":{"model":"DIW Loss","paper":"/paper/increasing-pedestrian-detection-performance","metrics":{"Heavy MR^-2":"28.37","Reasonable MR^-2":"6.23","Small MR^-2":"7.36"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/object-detection-on-citypersons","task":"Object Detection","dataset_variant":"CityPersons","rows":1,"metrics":["mMR"],"first_row_in_archive_order":{"model":"V2F-Net","paper":"/paper/v2f-net-explicit-decomposition-of-occluded","metrics":{"mMR":"10.08"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/vlpd-context-aware-pedestrian-detection-via","title":"VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision","date":"2023-04-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/beyond-appearance-a-semantic-controllable","title":"Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks","date":"2023-03-30","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/localized-semantic-feature-mixers-for","title":"Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving","date":"2023-01-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/increasing-pedestrian-detection-performance","title":"Increasing pedestrian detection performance through weighting of detection impairing factors","date":"2022-12-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"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/f2dnet-fast-focal-detection-network-for","title":"F2DNet: Fast Focal Detection Network for Pedestrian Detection","date":"2022-03-04","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/nms-loss-learning-with-non-maximum","title":"NMS-Loss: Learning with Non-Maximum Suppression for Crowded Pedestrian Detection","date":"2021-06-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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/pedestrian-detection-the-elephant-in-the-room","title":"Generalizable Pedestrian Detection: The Elephant In The Room","date":"2020-03-19","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/adapted-center-and-scale-prediction-more","title":"Adapted Center and Scale Prediction: More Stable and More Accurate","date":"2020-02-20","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/high-level-semantic-feature-detectiona-new","title":"Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection","date":"2019-04-05","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/learning-efficient-single-stage-pedestrian","title":"Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting","date":"2018-09-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/occlusion-aware-r-cnn-detecting-pedestrians","title":"Occlusion-aware R-CNN: Detecting Pedestrians in a Crowd","date":"2018-07-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/small-scale-pedestrian-detection-based-on","title":"Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation","date":"2018-07-04","rows_on_this_dataset":2,"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},{"paper":"/paper/repulsion-loss-detecting-pedestrians-in-a","title":"Repulsion Loss: Detecting Pedestrians in a Crowd","date":"2017-11-21","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/citypersons-a-diverse-dataset-for-pedestrian","title":"CityPersons: A Diverse Dataset for Pedestrian Detection","date":"2017-02-19","rows_on_this_dataset":2,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":6,"samples_ran":2,"samples_unverified":4,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":0,"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."}