{"url":"/task/crowd-counting","name":"Crowd Counting","slug":"crowd-counting","description_markdown":"**Crowd Counting** is a task to count people in image. It is mainly used in real-life for automated public monitoring such as surveillance and traffic control. Different from object detection, Crowd Counting aims at recognizing arbitrarily sized targets in various situations including sparse and cluttering scenes at the same time.\r\n\r\n\r\n<span class=\"description-source\">Source: [Deep Density-aware Count Regressor ](https://arxiv.org/abs/1908.03314)</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":371,"papers_with_code":154,"benchmarks":13,"benchmark_tables_in_archive":13,"benchmark_tables_shown":13,"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":23,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/crowd-counting-on-shanghaitech-a","slug":"crowd-counting-on-shanghaitech-a","dataset":"ShanghaiTech A","dataset_url":"/dataset/shanghaitech","rows_in_archive":35,"metrics":["MAE","MSE","RMSE"],"first_row_in_archive_order":{"model":"EBC-ZIP-B","paper_title":"EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression","paper_url":"/paper/ebc-zip-improving-blockwise-crowd-counting","paper_date":"2025-06-24","arxiv_id":"2506.19955","code_links":[{"title":"yiming-m/ebc-zip","url":"https://github.com/yiming-m/ebc-zip"}],"syntology":null}},{"leaderboard":"/sota/crowd-counting-on-shanghaitech-b","slug":"crowd-counting-on-shanghaitech-b","dataset":"ShanghaiTech B","dataset_url":"/dataset/shanghaitech","rows_in_archive":32,"metrics":["MAE","MSE","RMSE"],"first_row_in_archive_order":{"model":"EBC-ZIP-B","paper_title":"EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression","paper_url":"/paper/ebc-zip-improving-blockwise-crowd-counting","paper_date":"2025-06-24","arxiv_id":"2506.19955","code_links":[{"title":"yiming-m/ebc-zip","url":"https://github.com/yiming-m/ebc-zip"}],"syntology":null}},{"leaderboard":"/sota/crowd-counting-on-ucf-qnrf","slug":"crowd-counting-on-ucf-qnrf","dataset":"UCF-QNRF","dataset_url":"/dataset/ucf-qnrf","rows_in_archive":23,"metrics":["MAE","RMSE","MSE"],"first_row_in_archive_order":{"model":"EBC-ZIP-B","paper_title":"EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression","paper_url":"/paper/ebc-zip-improving-blockwise-crowd-counting","paper_date":"2025-06-24","arxiv_id":"2506.19955","code_links":[{"title":"yiming-m/ebc-zip","url":"https://github.com/yiming-m/ebc-zip"}],"syntology":null}},{"leaderboard":"/sota/crowd-counting-on-ucf-cc-50","slug":"crowd-counting-on-ucf-cc-50","dataset":"UCF CC 50","dataset_url":null,"rows_in_archive":22,"metrics":["MAE","MSE"],"first_row_in_archive_order":{"model":"APGCC","paper_title":"Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance","paper_url":"/paper/improving-point-based-crowd-counting-and","paper_date":"2024-05-17","arxiv_id":"2405.10589","code_links":[{"title":"AaronCIH/APGCC","url":"https://github.com/AaronCIH/APGCC"}],"syntology":null}},{"leaderboard":"/sota/crowd-counting-on-worldexpo10","slug":"crowd-counting-on-worldexpo10","dataset":"WorldExpo’10","dataset_url":null,"rows_in_archive":15,"metrics":["Average MAE"],"first_row_in_archive_order":{"model":"ECAN","paper_title":"Context-Aware Crowd Counting","paper_url":"/paper/context-aware-crowd-counting","paper_date":"2018-11-26","arxiv_id":"1811.10452","code_links":[{"title":"weizheliu/Context-Aware-Crowd-Counting","url":"https://github.com/weizheliu/Context-Aware-Crowd-Counting"},{"title":"CommissarMa/Context-Aware_Crowd_Counting-pytorch","url":"https://github.com/CommissarMa/Context-Aware_Crowd_Counting-pytorch"},{"title":"xr0927/chapter9-learnCVPR2019-Context-Aware_Crowd_Counting","url":"https://github.com/xr0927/chapter9-learnCVPR2019-Context-Aware_Crowd_Counting"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/crowd-counting-on-nwpu-crowd-val","slug":"crowd-counting-on-nwpu-crowd-val","dataset":"NWPU-Crowd (Val)","dataset_url":"/dataset/nwpu-crowd","rows_in_archive":6,"metrics":["MAE","RMSE"],"first_row_in_archive_order":{"model":"EBC-ZIP-B","paper_title":"EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression","paper_url":"/paper/ebc-zip-improving-blockwise-crowd-counting","paper_date":"2025-06-24","arxiv_id":"2506.19955","code_links":[{"title":"yiming-m/ebc-zip","url":"https://github.com/yiming-m/ebc-zip"}],"syntology":null}},{"leaderboard":"/sota/crowd-counting-on-dlr-acd","slug":"crowd-counting-on-dlr-acd","dataset":"DLR-ACD","dataset_url":"/dataset/dlr-acd","rows_in_archive":5,"metrics":["F1-score","MAE","MNAE","Precision","RMSE","Recall"],"first_row_in_archive_order":{"model":"MRCNet (ours)","paper_title":"MRCNet: Crowd Counting and Density Map Estimation in Aerial and Ground Imagery","paper_url":"/paper/mrcnet-crowd-counting-and-density-map","paper_date":"2019-09-27","arxiv_id":"1909.12743","code_links":[{"title":"gpspelle/Crowd-Counting","url":"https://github.com/gpspelle/Crowd-Counting"}],"syntology":null}},{"leaderboard":"/sota/crowd-counting-on-venice","slug":"crowd-counting-on-venice","dataset":"Venice","dataset_url":null,"rows_in_archive":5,"metrics":["MAE"],"first_row_in_archive_order":{"model":"ECAN","paper_title":"Context-Aware Crowd Counting","paper_url":"/paper/context-aware-crowd-counting","paper_date":"2018-11-26","arxiv_id":"1811.10452","code_links":[{"title":"weizheliu/Context-Aware-Crowd-Counting","url":"https://github.com/weizheliu/Context-Aware-Crowd-Counting"},{"title":"CommissarMa/Context-Aware_Crowd_Counting-pytorch","url":"https://github.com/CommissarMa/Context-Aware_Crowd_Counting-pytorch"},{"title":"xr0927/chapter9-learnCVPR2019-Context-Aware_Crowd_Counting","url":"https://github.com/xr0927/chapter9-learnCVPR2019-Context-Aware_Crowd_Counting"}],"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}}},{"leaderboard":"/sota/crowd-counting-on-trancos","slug":"crowd-counting-on-trancos","dataset":"TRANCOS","dataset_url":"/dataset/trancos","rows_in_archive":4,"metrics":["MAE"],"first_row_in_archive_order":{"model":"M-SFANet+M-SegNet","paper_title":"Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting","paper_url":"/paper/encoder-decoder-based-convolutional-neural","paper_date":"2020-03-12","arxiv_id":"2003.05586","code_links":[{"title":"Pongpisit-Thanasutives/Variations-of-SFANet-for-Crowd-Counting","url":"https://github.com/Pongpisit-Thanasutives/Variations-of-SFANet-for-Crowd-Counting"},{"title":"HuynhKEn/Variations-of-SFANet-for-Crowd-Counting","url":"https://github.com/HuynhKEn/Variations-of-SFANet-for-Crowd-Counting"}],"syntology":null}},{"leaderboard":"/sota/crowd-counting-on-jhu-crowd","slug":"crowd-counting-on-jhu-crowd","dataset":"JHU-CROWD++","dataset_url":"/dataset/jhu-crowd-1","rows_in_archive":3,"metrics":["MAE","MSE","MSE "],"first_row_in_archive_order":{"model":"EffCC-Lite0.5","paper_title":"Improved Knowledge Distillation for Crowd Counting on IoT Device","paper_url":"/paper/improved-knowledge-distillation-for-crowd","paper_date":"2023-08-02","arxiv_id":null,"code_links":[{"title":"huangzuo/effcc_distilled","url":"https://github.com/huangzuo/effcc_distilled"}],"syntology":null}},{"leaderboard":"/sota/crowd-counting-on-up-count","slug":"crowd-counting-on-up-count","dataset":"UP-COUNT","dataset_url":"/dataset/up-count","rows_in_archive":3,"metrics":["L-AP@10"],"first_row_in_archive_order":{"model":"STNNet","paper_title":"Detection, Tracking, and Counting Meets Drones in Crowds: A Benchmark","paper_url":"/paper/detection-tracking-and-counting-meets-drones","paper_date":"2021-05-06","arxiv_id":"2105.02440","code_links":[{"title":"VisDrone/DroneCrowd","url":"https://github.com/VisDrone/DroneCrowd"}],"syntology":null}},{"leaderboard":"/sota/crowd-counting-on-dronergbt","slug":"crowd-counting-on-dronergbt","dataset":"DroneRGBT","dataset_url":"/dataset/dronergbt","rows_in_archive":1,"metrics":["10.83"],"first_row_in_archive_order":{"model":"P2PNet","paper_title":"Transformer-Based Dual-Optical Attention Fusion Crowd Head Point Counting and Localization Network","paper_url":"/paper/transformer-based-dual-optical-attention","paper_date":"2025-05-11","arxiv_id":"2505.06937","code_links":[{"title":"zz-zik/tapnet","url":"https://github.com/zz-zik/tapnet"}],"syntology":null}},{"leaderboard":"/sota/crowd-counting-on-nwpu-crowd","slug":"crowd-counting-on-nwpu-crowd","dataset":"NWPU-Crowd","dataset_url":"/dataset/nwpu-crowd","rows_in_archive":1,"metrics":["MAE","MSE"],"first_row_in_archive_order":{"model":"APGCC","paper_title":"Improving Point-based Crowd Counting and Localization Based on Auxiliary Point Guidance","paper_url":"/paper/improving-point-based-crowd-counting-and","paper_date":"2024-05-17","arxiv_id":"2405.10589","code_links":[{"title":"AaronCIH/APGCC","url":"https://github.com/AaronCIH/APGCC"}],"syntology":null}}],"datasets":[{"url":"/dataset/shanghaitech","name":"ShanghaiTech","full_name":"","num_papers_in_archive":277},{"url":"/dataset/ucf-qnrf","name":"UCF-QNRF","full_name":"","num_papers_in_archive":176},{"url":"/dataset/jhu-crowd-1","name":"JHU-CROWD++","full_name":"","num_papers_in_archive":48},{"url":"/dataset/nwpu-crowd","name":"NWPU-Crowd","full_name":"","num_papers_in_archive":32},{"url":"/dataset/ucf-cc-50-1","name":"UCF-CC-50","full_name":"UCF-CC-50","num_papers_in_archive":32},{"url":"/dataset/jhu-crowd","name":"JHU-CROWD","full_name":"","num_papers_in_archive":22},{"url":"/dataset/fdst","name":"FDST","full_name":"Fudan-ShanghaiTech","num_papers_in_archive":18},{"url":"/dataset/citystreet","name":"CityStreet","full_name":"","num_papers_in_archive":12},{"url":"/dataset/cvcs","name":"CVCS","full_name":"Cross-View Cross-Scene Multi-View Crowd Counting Dataset","num_papers_in_archive":10},{"url":"/dataset/trancos","name":"TRANCOS","full_name":"TRaffic ANd COngestionS","num_papers_in_archive":7},{"url":"/dataset/dlr-acd","name":"DLR-ACD","full_name":"","num_papers_in_archive":6},{"url":"/dataset/dronecrowd","name":"DroneCrowd","full_name":"","num_papers_in_archive":6},{"url":"/dataset/scut-head","name":"SCUT-HEAD","full_name":"","num_papers_in_archive":6},{"url":"/dataset/www-crowd","name":"WWW Crowd","full_name":"WWW Crowd","num_papers_in_archive":5},{"url":"/dataset/crowdflow","name":"CrowdFlow","full_name":"TUB CrowdFlow","num_papers_in_archive":4},{"url":"/dataset/up-count","name":"UP-COUNT","full_name":"","num_papers_in_archive":3},{"url":"/dataset/cityuhk-x-bev","name":"CityUHK-X-BEV","full_name":"","num_papers_in_archive":2},{"url":"/dataset/multi-task-crowd","name":"Multi Task Crowd","full_name":"","num_papers_in_archive":2},{"url":"/dataset/rsoc","name":"RSOC","full_name":"Remote Sensing Object Counting","num_papers_in_archive":2},{"url":"/dataset/smartcity","name":"SmartCity","full_name":"","num_papers_in_archive":2},{"url":"/dataset/cross-view-cross-scene-multi-view-crowd","name":"Cross-View Cross-Scene Multi-View Crowd Counting Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/dronergbt","name":"DroneRGBT","full_name":"DroneRGBT","num_papers_in_archive":1},{"url":"/dataset/crowd-in-a-rally-crowd-counting-crowd-human","name":"Crowd in a rally | Crowd Counting | Crowd Human","full_name":"datacluster.ai","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/crowds","name":"Crowds"}],"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":154,"tagged_in_all":371,"items":[{"url":"/paper/densely-connected-convolutional-networks","title":"Densely Connected Convolutional Networks","date":"2016-08-25","arxiv_id":"1608.06993","repositories_listed":146,"syntology":{"n":71,"n_ran":18,"n_unverified":53,"n_pointer_only":7}},{"url":"/paper/segnet-a-deep-convolutional-encoder-decoder","title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","date":"2015-11-02","arxiv_id":"1511.00561","repositories_listed":74,"syntology":{"n":44,"n_ran":9,"n_unverified":35,"n_pointer_only":10}},{"url":"/paper/csrnet-dilated-convolutional-neural-networks","title":"CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes","date":"2018-02-27","arxiv_id":"1802.10062","repositories_listed":11,"syntology":{"n":15,"n_ran":5,"n_unverified":10,"n_pointer_only":5}},{"url":"/paper/from-open-set-to-closed-set-counting-objects","title":"From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer","date":"2019-08-15","arxiv_id":"1908.06473","repositories_listed":5,"syntology":{"n":8,"n_ran":3,"n_unverified":5,"n_pointer_only":3}},{"url":"/paper/nwpu-crowd-a-large-scale-benchmark-for-crowd","title":"NWPU-Crowd: A Large-Scale Benchmark for Crowd Counting and Localization","date":"2020-01-10","arxiv_id":"2001.03360","repositories_listed":4,"syntology":{"n":10,"n_ran":5,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/single-image-crowd-counting-via-multi-column-1","title":"Single-Image Crowd Counting via Multi-Column Convolutional Neural Network","date":"2016-01-01","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/inception-based-crowd-counting-being-fast","title":"Inception-Based Crowd Counting -- Being Fast while Remaining Accurate","date":"2022-10-18","arxiv_id":"2210.09796","repositories_listed":3,"syntology":null},{"url":"/paper/uniformity-in-heterogeneity-diving-deep-into","title":"Uniformity in Heterogeneity:Diving Deep into Count Interval Partition for Crowd Counting","date":"2021-07-27","arxiv_id":"2107.12619","repositories_listed":3,"syntology":null},{"url":"/paper/rethinking-counting-and-localization-in","title":"Rethinking Counting and Localization in Crowds:A Purely Point-Based Framework","date":"2021-07-27","arxiv_id":"2107.12746","repositories_listed":3,"syntology":null},{"url":"/paper/reciprocal-distance-transform-maps-for-crowd","title":"Focal Inverse Distance Transform Maps for Crowd Localization","date":"2021-02-16","arxiv_id":"2102.07925","repositories_listed":3,"syntology":null},{"url":"/paper/cnn-based-density-estimation-and-crowd","title":"CNN-based Density Estimation and Crowd Counting: A Survey","date":"2020-03-28","arxiv_id":"2003.12783","repositories_listed":3,"syntology":null},{"url":"/paper/c3-framework-an-open-source-pytorch-code-for","title":"C^3 Framework: An Open-source PyTorch Code for Crowd Counting","date":"2019-07-05","arxiv_id":"1907.02724","repositories_listed":3,"syntology":null},{"url":"/paper/context-aware-crowd-counting","title":"Context-Aware Crowd Counting","date":"2018-11-26","arxiv_id":"1811.10452","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/crowdclip-unsupervised-crowd-counting-via","title":"CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model","date":"2023-04-09","arxiv_id":"2304.04231","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/dr-vic-decomposition-and-reasoning-for-video","title":"DR.VIC: Decomposition and Reasoning for Video Individual Counting","date":"2022-03-23","arxiv_id":"2203.12335","repositories_listed":2,"syntology":{"n":11,"n_ran":6,"n_unverified":5,"n_pointer_only":11}},{"url":"/paper/s-2-fpr-crowd-counting-via-self-supervised","title":"Deep Rank-Consistent Pyramid Model for Enhanced Crowd Counting","date":"2022-01-13","arxiv_id":"2201.04819","repositories_listed":2,"syntology":null},{"url":"/paper/cctrans-simplifying-and-improving-crowd","title":"CCTrans: Simplifying and Improving Crowd Counting with Transformer","date":"2021-09-29","arxiv_id":"2109.14483","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":2}},{"url":"/paper/a-self-training-approach-for-point-supervised","title":"A Self-Training Approach for Point-Supervised Object Detection and Counting in Crowds","date":"2020-07-25","arxiv_id":"2007.12831","repositories_listed":2,"syntology":null},{"url":"/paper/pyramid-scale-network-for-crowd-counting","title":"Exploit the potential of Multi-column architecture for Crowd Counting","date":"2020-07-11","arxiv_id":"2007.05779","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-crowd-counting-via-structured","title":"Efficient Crowd Counting via Structured Knowledge Transfer","date":"2020-03-23","arxiv_id":"2003.10120","repositories_listed":2,"syntology":null},{"url":"/paper/encoder-decoder-based-convolutional-neural","title":"Encoder-Decoder Based Convolutional Neural Networks with Multi-Scale-Aware Modules for Crowd Counting","date":"2020-03-12","arxiv_id":"2003.05586","repositories_listed":2,"syntology":null},{"url":"/paper/autoscale-learning-to-scale-for-crowd","title":"AutoScale: Learning to Scale for Crowd Counting and Localization","date":"2019-12-20","arxiv_id":"1912.09632","repositories_listed":2,"syntology":null},{"url":"/paper/bayesian-loss-for-crowd-count-estimation-with","title":"Bayesian Loss for Crowd Count Estimation with Point Supervision","date":"2019-08-10","arxiv_id":"1908.03684","repositories_listed":2,"syntology":null},{"url":"/paper/locate-size-and-count-accurately-resolving","title":"Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection","date":"2019-06-18","arxiv_id":"1906.07538","repositories_listed":2,"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/exploiting-unlabeled-data-in-cnns-by-self","title":"Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank","date":"2019-02-17","arxiv_id":"1902.06285","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/dual-path-multi-scale-fusion-networks-with","title":"Dual Path Multi-Scale Fusion Networks with Attention for Crowd Counting","date":"2019-02-04","arxiv_id":"1902.01115","repositories_listed":2,"syntology":null},{"url":"/paper/improving-object-counting-with-heatmap","title":"Improving Object Counting with Heatmap Regulation","date":"2018-03-14","arxiv_id":"1803.05494","repositories_listed":2,"syntology":null},{"url":"/paper/crowdnet-a-deep-convolutional-network-for","title":"CrowdNet: A Deep Convolutional Network for Dense Crowd Counting","date":"2016-08-22","arxiv_id":"1608.06197","repositories_listed":2,"syntology":null},{"url":"/paper/car-object-counting-and-position-estimation","title":"Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework","date":"2025-07-11","arxiv_id":"2507.08240","repositories_listed":1,"syntology":null},{"url":"/paper/ebc-zip-improving-blockwise-crowd-counting","title":"EBC-ZIP: Improving Blockwise Crowd Counting with Zero-Inflated Poisson Regression","date":"2025-06-24","arxiv_id":"2506.19955","repositories_listed":1,"syntology":null}],"syntology_records":11,"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":0,"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"}}