{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/crowd-counting-via-scale-adaptive","title":"Crowd counting via scale-adaptive convolutional neural network","arxiv_id":"1711.04433","date":"2017-11-13","proceeding":null,"authors":["Lu Zhang","Miaojing Shi","Qiaobo Chen"],"abstract":"The task of crowd counting is to automatically estimate the pedestrian number\nin crowd images. To cope with the scale and perspective changes that commonly\nexist in crowd images, state-of-the-art approaches employ multi-column CNN\narchitectures to regress density maps of crowd images. Multiple columns have\ndifferent receptive fields corresponding to pedestrians (heads) of different\nscales. We instead propose a scale-adaptive CNN (SaCNN) architecture with a\nbackbone of fixed small receptive fields. We extract feature maps from multiple\nlayers and adapt them to have the same output size; we combine them to produce\nthe final density map. The number of people is computed by integrating the\ndensity map. We also introduce a relative count loss along with the density map\nloss to improve the network generalization on crowd scenes with few\npedestrians, where most representative approaches perform poorly on. We conduct\nextensive experiments on the ShanghaiTech, UCF_CC_50 and WorldExpo datasets as\nwell as a new dataset SmartCity that we collect for crowd scenes with few\npeople. The results demonstrate significant improvements of SaCNN over the\nstate-of-the-art.","url_abs":"http://arxiv.org/abs/1711.04433v4","url_pdf":"http://arxiv.org/pdf/1711.04433v4.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":"crowd-counting-via-scale-adaptive","repo_url":"https://github.com/miao0913/SaCNN-CrowdCounting-Tencent_Youtu","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"}],"methods":[],"datasets_introduced":[{"slug":"smartcity","name":"SmartCity","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1711.04433","atlas_url":"https://app.syntology.ai/?focus=1711.04433","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1711.04433"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1711.04433\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1711.04433"},"call":"get_concepts_for_paper(arxiv_id=\"1711.04433\")"}],"by_repo":[{"repo":"miao0913/SaCNN-CrowdCounting-Tencent_Youtu","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1fec7910bd1edefcc3a9188629e5f302f72e2b832ed4ba85d9245b8254cd6cef","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}