{"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/crowdnet-a-deep-convolutional-network-for","title":"CrowdNet: A Deep Convolutional Network for Dense Crowd Counting","arxiv_id":"1608.06197","date":"2016-08-22","proceeding":null,"authors":["Lokesh Boominathan","Srinivas S. S. Kruthiventi","R. Venkatesh Babu"],"abstract":"Our work proposes a novel deep learning framework for estimating crowd\ndensity from static images of highly dense crowds. We use a combination of deep\nand shallow, fully convolutional networks to predict the density map for a\ngiven crowd image. Such a combination is used for effectively capturing both\nthe high-level semantic information (face/body detectors) and the low-level\nfeatures (blob detectors), that are necessary for crowd counting under large\nscale variations. As most crowd datasets have limited training samples (<100\nimages) and deep learning based approaches require large amounts of training\ndata, we perform multi-scale data augmentation. Augmenting the training samples\nin such a manner helps in guiding the CNN to learn scale invariant\nrepresentations. Our method is tested on the challenging UCF_CC_50 dataset, and\nshown to outperform the state of the art methods.","url_abs":"http://arxiv.org/abs/1608.06197v1","url_pdf":"http://arxiv.org/pdf/1608.06197v1.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":"crowdnet-a-deep-convolutional-network-for","repo_url":"https://github.com/davideverona/deep-crowd-counting_crowdnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"crowdnet-a-deep-convolutional-network-for","repo_url":"https://github.com/violin0847/crowdcounting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"crowd-counting","task_name":"Crowd Counting"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"deep-learning","task_name":"Deep Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.06197","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}