{"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/switching-convolutional-neural-network-for","title":"Switching Convolutional Neural Network for Crowd Counting","arxiv_id":"1708.00199","date":"2017-08-01","proceeding":"CVPR 2017 7","authors":["Deepak Babu Sam","Shiv Surya","R. Venkatesh Babu"],"abstract":"We propose a novel crowd counting model that maps a given crowd scene to its\ndensity. Crowd analysis is compounded by myriad of factors like inter-occlusion\nbetween people due to extreme crowding, high similarity of appearance between\npeople and background elements, and large variability of camera view-points.\nCurrent state-of-the art approaches tackle these factors by using multi-scale\nCNN architectures, recurrent networks and late fusion of features from\nmulti-column CNN with different receptive fields. We propose switching\nconvolutional neural network that leverages variation of crowd density within\nan image to improve the accuracy and localization of the predicted crowd count.\nPatches from a grid within a crowd scene are relayed to independent CNN\nregressors based on crowd count prediction quality of the CNN established\nduring training. The independent CNN regressors are designed to have different\nreceptive fields and a switch classifier is trained to relay the crowd scene\npatch to the best CNN regressor. We perform extensive experiments on all major\ncrowd counting datasets and evidence better performance compared to current\nstate-of-the-art methods. We provide interpretable representations of the\nmultichotomy of space of crowd scene patches inferred from the switch. It is\nobserved that the switch relays an image patch to a particular CNN column based\non density of crowd.","url_abs":"http://arxiv.org/abs/1708.00199v2","url_pdf":"http://arxiv.org/pdf/1708.00199v2.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":"switching-convolutional-neural-network-for","repo_url":"https://github.com/val-iisc/crowd-counting-scnn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/crowd-counting-on-shanghaitech-a","task":"Crowd Counting","dataset":"ShanghaiTech A","model":"Switch-CNN","rank_in_archive_order":32,"of":35,"metrics":{"MAE":"90.4"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-shanghaitech-b","task":"Crowd Counting","dataset":"ShanghaiTech B","model":"Switch-CNN","rank_in_archive_order":30,"of":32,"metrics":{"MAE":"21.6"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-ucf-cc-50","task":"Crowd Counting","dataset":"UCF CC 50","model":"Switch-CNN","rank_in_archive_order":17,"of":22,"metrics":{"MAE":"318.1"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-ucf-qnrf","task":"Crowd Counting","dataset":"UCF-QNRF","model":"Switch-CNN","rank_in_archive_order":19,"of":23,"metrics":{"MAE":"228"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-venice","task":"Crowd Counting","dataset":"Venice","model":"Switch-CNN","rank_in_archive_order":4,"of":5,"metrics":{"MAE":"52.8"},"uses_additional_data":false},{"leaderboard":"/sota/crowd-counting-on-worldexpo10","task":"Crowd Counting","dataset":"WorldExpo’10","model":"Switch-CNN","rank_in_archive_order":11,"of":15,"metrics":{"Average MAE":"9.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.00199","atlas_url":"https://app.syntology.ai/?focus=1708.00199","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":"1708.00199"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1708.00199\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1708.00199"},"call":"get_concepts_for_paper(arxiv_id=\"1708.00199\")"}],"by_repo":[{"repo":"val-iisc/crowd-counting-scnn","kind":"listed","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":"2b3259cdd27113972d549759b8faca9905ab1849cf7300a8fad327013c20bf59","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}