{"url":"/task/pedestrian-detection","name":"Pedestrian Detection","slug":"pedestrian-detection","description_markdown":"Pedestrian detection is the task of detecting pedestrians from a camera.\r\n\r\nFurther state-of-the-art results (e.g. on the KITTI dataset) can be found at [3D Object Detection](https://paperswithcode.com/task/object-detection).\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection](https://github.com/liuwei16/CSP) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":438,"papers_with_code":132,"benchmarks":9,"benchmark_tables_in_archive":9,"benchmark_tables_shown":9,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":17,"subtasks":1,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/pedestrian-detection-on-caltech","slug":"pedestrian-detection-on-caltech","dataset":"Caltech","dataset_url":null,"rows_in_archive":33,"metrics":["Reasonable Miss Rate","Heavy MR^-2"],"first_row_in_archive_order":{"model":"LSFM","paper_title":"Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving","paper_url":"/paper/localized-semantic-feature-mixers-for","paper_date":"2023-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/pedestrian-detection-on-citypersons","slug":"pedestrian-detection-on-citypersons","dataset":"CityPersons","dataset_url":"/dataset/citypersons","rows_in_archive":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_title":"Increasing pedestrian detection performance through weighting of detection impairing factors","paper_url":"/paper/increasing-pedestrian-detection-performance","paper_date":"2022-12-08","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/pedestrian-detection-on-llvip","slug":"pedestrian-detection-on-llvip","dataset":"LLVIP","dataset_url":"/dataset/llvip","rows_in_archive":15,"metrics":["AP","log average miss rate"],"first_row_in_archive_order":{"model":"MMPedestron","paper_title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","paper_url":"/paper/when-pedestrian-detection-meets-multi-modal","paper_date":"2024-07-14","arxiv_id":"2407.10125","code_links":[{"title":"BubblyYi/MMPedestron","url":"https://github.com/BubblyYi/MMPedestron"}],"syntology":null}},{"leaderboard":"/sota/pedestrian-detection-on-dvtod","slug":"pedestrian-detection-on-dvtod","dataset":"DVTOD","dataset_url":null,"rows_in_archive":8,"metrics":[" mAP","mAP"],"first_row_in_archive_order":{"model":"YOLOv6 (Thermal)","paper_title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","paper_url":"/paper/yolov6-a-single-stage-object-detection","paper_date":"2022-09-07","arxiv_id":"2209.02976","code_links":[{"title":"PaddlePaddle/PaddleDetection","url":"https://github.com/PaddlePaddle/PaddleDetection"},{"title":"meituan/yolov6","url":"https://github.com/meituan/yolov6"},{"title":"open-mmlab/mmyolo","url":"https://github.com/open-mmlab/mmyolo"},{"title":"PaddlePaddle/PaddleYOLO","url":"https://github.com/PaddlePaddle/PaddleYOLO"},{"title":"yang-0201/YOLOv6_pro","url":"https://github.com/yang-0201/YOLOv6_pro"},{"title":"CycloneBoy/PPDetectionPytorch","url":"https://github.com/CycloneBoy/PPDetectionPytorch"},{"title":"kadirnar/yolov6-pip","url":"https://github.com/kadirnar/yolov6-pip"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}}},{"leaderboard":"/sota/pedestrian-detection-on-tju-ped-traffic","slug":"pedestrian-detection-on-tju-ped-traffic","dataset":"TJU-Ped-traffic","dataset_url":"/dataset/tju-dhd","rows_in_archive":6,"metrics":["R (miss rate)","RS (miss rate)","HO (miss rate)","R+HO (miss rate)","ALL (miss rate)"],"first_row_in_archive_order":{"model":"LSFM","paper_title":"Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving","paper_url":"/paper/localized-semantic-feature-mixers-for","paper_date":"2023-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/pedestrian-detection-on-tju-ped-campus","slug":"pedestrian-detection-on-tju-ped-campus","dataset":"TJU-Ped-campus","dataset_url":"/dataset/tju-dhd","rows_in_archive":4,"metrics":["R (miss rate)","RS (miss rate)","HO (miss rate)","R+HO (miss rate)","ALL (miss rate)"],"first_row_in_archive_order":{"model":"EGCL","paper_title":"Pedestrian Detection by Exemplar-Guided Contrastive Learning","paper_url":"/paper/pedestrian-detection-by-exemplar-guided","paper_date":"2021-11-17","arxiv_id":"2111.08974","code_links":[],"syntology":null}},{"leaderboard":"/sota/pedestrian-detection-on-cvc14","slug":"pedestrian-detection-on-cvc14","dataset":"CVC14","dataset_url":null,"rows_in_archive":2,"metrics":["AP50"],"first_row_in_archive_order":{"model":"CFT","paper_title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","paper_url":"/paper/cross-modality-fusion-transformer-for","paper_date":"2021-10-30","arxiv_id":"2111.00273","code_links":[{"title":"docf/multispectral-object-detection","url":"https://github.com/docf/multispectral-object-detection"}],"syntology":null}},{"leaderboard":"/sota/pedestrian-detection-on-caltech-pedestrian","slug":"pedestrian-detection-on-caltech-pedestrian","dataset":"Caltech Pedestrian Dataset","dataset_url":"/dataset/caltech-pedestrian-dataset","rows_in_archive":1,"metrics":["MR"],"first_row_in_archive_order":{"model":"LSFM","paper_title":"Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving","paper_url":"/paper/localized-semantic-feature-mixers-for","paper_date":"2023-01-01","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/pedestrian-detection-on-mmpd-dataset","slug":"pedestrian-detection-on-mmpd-dataset","dataset":"MMPD-Dataset","dataset_url":"/dataset/mmpd-dataset","rows_in_archive":1,"metrics":["box mAP"],"first_row_in_archive_order":{"model":"MMPedestron","paper_title":"When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Dataset","paper_url":"/paper/when-pedestrian-detection-meets-multi-modal","paper_date":"2024-07-14","arxiv_id":"2407.10125","code_links":[{"title":"BubblyYi/MMPedestron","url":"https://github.com/BubblyYi/MMPedestron"}],"syntology":null}}],"datasets":[{"url":"/dataset/citypersons","name":"CityPersons","full_name":"","num_papers_in_archive":129},{"url":"/dataset/llvip","name":"LLVIP","full_name":"A Visible-infrared Paired Dataset for Low-light Vision","num_papers_in_archive":116},{"url":"/dataset/prw","name":"PRW","full_name":"Person Re-identification in the Wild","num_papers_in_archive":77},{"url":"/dataset/eth","name":"ETH","full_name":"ETH Pedestrian","num_papers_in_archive":58},{"url":"/dataset/inria-person","name":"INRIA Person","full_name":"","num_papers_in_archive":24},{"url":"/dataset/cadp","name":"CADP","full_name":"","num_papers_in_archive":14},{"url":"/dataset/tju-dhd","name":"TJU-DHD","full_name":null,"num_papers_in_archive":12},{"url":"/dataset/eurocity-persons","name":"EuroCity Persons","full_name":"","num_papers_in_archive":6},{"url":"/dataset/caltech-pedestrian-dataset","name":"Caltech Pedestrian Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/raileye3d-dataset","name":"RailEye3D Dataset","full_name":"","num_papers_in_archive":3},{"url":"/dataset/bgvp","name":"BGVP","full_name":"BG Vulnerable Pedestrian","num_papers_in_archive":2},{"url":"/dataset/uoftped50","name":"UofTPed50","full_name":"","num_papers_in_archive":2},{"url":"/dataset/mmpd-dataset","name":"MMPD-Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nrec-agricultural-person-detection","name":"NREC Agricultural Person-Detection","full_name":"","num_papers_in_archive":1},{"url":"/dataset/synoclip","name":"SynoClip","full_name":"","num_papers_in_archive":1},{"url":"/dataset/virtual-pedcross-4667","name":"Virtual-Pedcross-4667","full_name":"","num_papers_in_archive":1},{"url":"/dataset/kaist-multi-spectral-2018","name":"KAIST multi-spectral Day/Night 2018","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/thermal-infrared-pedestrian-detection","name":"Thermal Infrared Pedestrian Detection"}],"parent_tasks":[{"url":"/task/autonomous-vehicles","name":"Autonomous Vehicles"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":132,"tagged_in_all":438,"items":[{"url":"/paper/yolov3-an-incremental-improvement","title":"YOLOv3: An Incremental Improvement","date":"2018-04-08","arxiv_id":"1804.02767","repositories_listed":311,"syntology":{"n":124,"n_ran":18,"n_unverified":106,"n_pointer_only":19}},{"url":"/paper/focal-loss-for-dense-object-detection","title":"Focal Loss for Dense Object Detection","date":"2017-08-07","arxiv_id":"1708.02002","repositories_listed":234,"syntology":{"n":11,"n_ran":11,"n_unverified":0,"n_pointer_only":6}},{"url":"/paper/fcos-fully-convolutional-one-stage-object","title":"FCOS: Fully Convolutional One-Stage Object Detection","date":"2019-04-02","arxiv_id":"1904.01355","repositories_listed":87,"syntology":{"n":40,"n_ran":13,"n_unverified":27,"n_pointer_only":18}},{"url":"/paper/feature-pyramid-networks-for-object-detection","title":"Feature Pyramid Networks for Object Detection","date":"2016-12-09","arxiv_id":"1612.03144","repositories_listed":85,"syntology":{"n":51,"n_ran":16,"n_unverified":35,"n_pointer_only":11}},{"url":"/paper/yolov7-trainable-bag-of-freebies-sets-new","title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","date":"2022-07-06","arxiv_id":"2207.02696","repositories_listed":21,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/yolov6-a-single-stage-object-detection","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","date":"2022-09-07","arxiv_id":"2209.02976","repositories_listed":7,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/fast-algorithms-for-convolutional-neural","title":"Fast Algorithms for Convolutional Neural Networks","date":"2015-09-30","arxiv_id":"1509.09308","repositories_listed":5,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}},{"url":"/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","arxiv_id":"2303.17602","repositories_listed":4,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/stcrowd-a-multimodal-dataset-for-pedestrian","title":"STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes","date":"2022-04-03","arxiv_id":"2204.01026","repositories_listed":4,"syntology":null},{"url":"/paper/exploring-visual-context-for-weakly","title":"Exploring Visual Context for Weakly Supervised Person Search","date":"2021-06-19","arxiv_id":"2106.10506","repositories_listed":3,"syntology":null},{"url":"/paper/multimodal-object-detection-via-bayesian","title":"Multimodal Object Detection via Probabilistic Ensembling","date":"2021-04-07","arxiv_id":"2104.02904","repositories_listed":3,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":8}},{"url":"/paper/multiview-detection-with-feature-perspective","title":"Multiview Detection with Feature Perspective Transformation","date":"2020-07-14","arxiv_id":"2007.07247","repositories_listed":3,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/detection-in-crowded-scenes-one-proposal","title":"Detection in Crowded Scenes: One Proposal, Multiple Predictions","date":"2020-03-20","arxiv_id":"2003.09163","repositories_listed":3,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/mask-guided-attention-network-for-occluded","title":"Mask-Guided Attention Network for Occluded Pedestrian Detection","date":"2019-10-14","arxiv_id":"1910.06160","repositories_listed":3,"syntology":null},{"url":"/paper/hulk-a-universal-knowledge-translator-for","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","date":"2023-12-04","arxiv_id":"2312.01697","repositories_listed":2,"syntology":{"n":24,"n_ran":12,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/dark-skin-individuals-are-at-more-risk-on-the","title":"Bias Behind the Wheel: Fairness Testing of Autonomous Driving Systems","date":"2023-08-05","arxiv_id":"2308.02935","repositories_listed":2,"syntology":null},{"url":"/paper/carla-bsp-a-simulated-dataset-with","title":"CARLA-BSP: a simulated dataset with pedestrians","date":"2023-04-29","arxiv_id":"2305.00204","repositories_listed":2,"syntology":null},{"url":"/paper/comparison-of-deep-object-detectors-on-a-new","title":"Comparison Of Deep Object Detectors On A New Vulnerable Pedestrian Dataset","date":"2022-12-12","arxiv_id":"2212.06218","repositories_listed":2,"syntology":null},{"url":"/paper/domain-adaptive-person-search","title":"Domain Adaptive Person Search","date":"2022-07-25","arxiv_id":"2207.11898","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":7}},{"url":"/paper/the-impact-of-partial-occlusion-on-pedestrian","title":"The Impact of Partial Occlusion on Pedestrian Detectability","date":"2022-05-10","arxiv_id":"2205.04812","repositories_listed":2,"syntology":null},{"url":"/paper/f2dnet-fast-focal-detection-network-for","title":"F2DNet: Fast Focal Detection Network for Pedestrian Detection","date":"2022-03-04","arxiv_id":"2203.02331","repositories_listed":2,"syntology":null},{"url":"/paper/graph-neural-networks-for-cross-camera-data","title":"Graph Neural Networks for Cross-Camera Data Association","date":"2022-01-17","arxiv_id":"2201.06311","repositories_listed":2,"syntology":null},{"url":"/paper/pedestrian-detection-domain-generalization","title":"Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond","date":"2022-01-10","arxiv_id":"2201.03176","repositories_listed":2,"syntology":null},{"url":"/paper/embracing-single-stride-3d-object-detector","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","date":"2021-12-13","arxiv_id":"2112.06375","repositories_listed":2,"syntology":null},{"url":"/paper/from-handcrafted-to-deep-features-for","title":"From Handcrafted to Deep Features for Pedestrian Detection: A Survey","date":"2020-10-01","arxiv_id":"2010.00456","repositories_listed":2,"syntology":null},{"url":"/paper/improving-multispectral-pedestrian-detection","title":"Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems","date":"2020-08-07","arxiv_id":"2008.03043","repositories_listed":2,"syntology":null},{"url":"/paper/occluded-prohibited-items-detection-an-x-ray","title":"Occluded Prohibited Items Detection: an X-ray Security Inspection Benchmark and De-occlusion Attention Module","date":"2020-04-18","arxiv_id":"2004.08656","repositories_listed":2,"syntology":null},{"url":"/paper/high-level-semantic-feature-detectiona-new","title":"Center and Scale Prediction: Anchor-free Approach for Pedestrian and Face Detection","date":"2019-04-05","arxiv_id":"1904.02948","repositories_listed":2,"syntology":null},{"url":"/paper/pedestrian-synthesis-gan-generating","title":"Pedestrian-Synthesis-GAN: Generating Pedestrian Data in Real Scene and Beyond","date":"2018-04-05","arxiv_id":"1804.02047","repositories_listed":2,"syntology":null},{"url":"/paper/repulsion-loss-detecting-pedestrians-in-a","title":"Repulsion Loss: Detecting Pedestrians in a Crowd","date":"2017-11-21","arxiv_id":"1711.07752","repositories_listed":2,"syntology":null}],"syntology_records":13,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}