{"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/context-aware-crowd-counting","title":"Context-Aware Crowd Counting","arxiv_id":"1811.10452","date":"2018-11-26","proceeding":"CVPR 2019 6","authors":["Weizhe Liu","Mathieu Salzmann","Pascal Fua"],"abstract":"State-of-the-art methods for counting people in crowded scenes rely on deep\nnetworks to estimate crowd density. They typically use the same filters over\nthe whole image or over large image patches. Only then do they estimate local\nscale to compensate for perspective distortion. This is typically achieved by\ntraining an auxiliary classifier to select, for predefined image patches, the\nbest kernel size among a limited set of choices. As such, these methods are not\nend-to-end trainable and restricted in the scope of context they can leverage.\n  In this paper, we introduce an end-to-end trainable deep architecture that\ncombines features obtained using multiple receptive field sizes and learns the\nimportance of each such feature at each image location. In other words, our\napproach adaptively encodes the scale of the contextual information required to\naccurately predict crowd density. This yields an algorithm that outperforms\nstate-of-the-art crowd counting methods, especially when perspective effects\nare strong.","url_abs":"http://arxiv.org/abs/1811.10452v2","url_pdf":"http://arxiv.org/pdf/1811.10452v2.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":[{"paper_slug":"context-aware-crowd-counting","repo_url":"https://github.com/weizheliu/Context-Aware-Crowd-Counting","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"context-aware-crowd-counting","repo_url":"https://github.com/CommissarMa/Context-Aware_Crowd_Counting-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"context-aware-crowd-counting","repo_url":"https://github.com/xr0927/chapter9-learnCVPR2019-Context-Aware_Crowd_Counting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"}],"methods":[{"method_slug":"auxiliary-classifier","method_name":"Auxiliary Classifier"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/crowd-counting-on-shanghaitech-a","task":"Crowd Counting","dataset":"ShanghaiTech A","model":"CAN","rank_in_archive_order":19,"of":35,"metrics":{"MAE":"62.3"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-shanghaitech-b","task":"Crowd Counting","dataset":"ShanghaiTech B","model":"CAN","rank_in_archive_order":16,"of":32,"metrics":{"MAE":"7.8"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-ucf-cc-50","task":"Crowd Counting","dataset":"UCF CC 50","model":"CAN","rank_in_archive_order":5,"of":22,"metrics":{"MAE":"212.2"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-ucf-qnrf","task":"Crowd Counting","dataset":"UCF-QNRF","model":"CAN","rank_in_archive_order":15,"of":23,"metrics":{"MAE":"107"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-venice","task":"Crowd Counting","dataset":"Venice","model":"ECAN","rank_in_archive_order":1,"of":5,"metrics":{"MAE":"20.5"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-venice","task":"Crowd Counting","dataset":"Venice","model":"CAN","rank_in_archive_order":2,"of":5,"metrics":{"MAE":"23.5"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-worldexpo10","task":"Crowd Counting","dataset":"WorldExpo’10","model":"ECAN","rank_in_archive_order":1,"of":15,"metrics":{"Average MAE":"7.2"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-worldexpo10","task":"Crowd Counting","dataset":"WorldExpo’10","model":"CAN","rank_in_archive_order":3,"of":15,"metrics":{"Average MAE":"7.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.10452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.10452"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xr0927/chapter9-learnCVPR2019-Context-Aware_Crowd_Counting","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/weizheliu/Context-Aware-Crowd-Counting","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CommissarMa/Context-Aware_Crowd_Counting-pytorch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"listed":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bd14ee2717325fe2","entry":"make_layers","repo":"CommissarMa/Context-Aware_Crowd_Counting-pytorch","repo_kind":"listed","path":"cannet.py","file_url":"https://github.com/CommissarMa/Context-Aware_Crowd_Counting-pytorch/blob/HEAD/cannet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd14ee2717325fe2"}},{"code_sha256_prefix":"15ea71d249d88c05","entry":"gaussian_filter_density","repo":"CommissarMa/Context-Aware_Crowd_Counting-pytorch","repo_kind":"listed","path":"data_preparation/k_nearest_gaussian_kernel.py","file_url":"https://github.com/CommissarMa/Context-Aware_Crowd_Counting-pytorch/blob/HEAD/data_preparation/k_nearest_gaussian_kernel.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"15ea71d249d88c05"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}