{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/iterative-crowd-counting","title":"Iterative Crowd Counting","arxiv_id":"1807.09959","date":"2018-07-26","proceeding":"ECCV 2018 9","authors":["Viresh Ranjan","Hieu Le","Minh Hoai"],"abstract":"In this work, we tackle the problem of crowd counting in images. We present a\nConvolutional Neural Network (CNN) based density estimation approach to solve\nthis problem. Predicting a high resolution density map in one go is a\nchallenging task. Hence, we present a two branch CNN architecture for\ngenerating high resolution density maps, where the first branch generates a low\nresolution density map, and the second branch incorporates the low resolution\nprediction and feature maps from the first branch to generate a high resolution\ndensity map. We also propose a multi-stage extension of our approach where each\nstage in the pipeline utilizes the predictions from all the previous stages.\nEmpirical comparison with the previous state-of-the-art crowd counting methods\nshows that our method achieves the lowest mean absolute error on three\nchallenging crowd counting benchmarks: Shanghaitech, WorldExpo'10, and UCF\ndatasets.","url_abs":"http://arxiv.org/abs/1807.09959v1","url_pdf":"http://arxiv.org/pdf/1807.09959v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"},{"task_slug":"density-estimation","task_name":"Density Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/crowd-counting-on-shanghaitech-a","task":"Crowd Counting","dataset":"ShanghaiTech A","model":"ic-CNN","rank_in_archive_order":25,"of":35,"metrics":{"MAE":"68.5"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-shanghaitech-b","task":"Crowd Counting","dataset":"ShanghaiTech B","model":"ic-CNN","rank_in_archive_order":23,"of":32,"metrics":{"MAE":"10.7"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-ucf-cc-50","task":"Crowd Counting","dataset":"UCF CC 50","model":"ic-CNN","rank_in_archive_order":11,"of":22,"metrics":{"MAE":"260.9"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-worldexpo10","task":"Crowd Counting","dataset":"WorldExpo’10","model":"ic-CNN","rank_in_archive_order":12,"of":15,"metrics":{"Average MAE":"10.3"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1807.09959","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}