{"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/taking-a-deeper-look-at-pedestrians","title":"Taking a Deeper Look at Pedestrians","arxiv_id":"1501.05790","date":"2015-01-23","proceeding":"CVPR 2015 6","authors":["Jan Hosang","Mohamed Omran","Rodrigo Benenson","Bernt Schiele"],"abstract":"In this paper we study the use of convolutional neural networks (convnets)\nfor the task of pedestrian detection. Despite their recent diverse successes,\nconvnets historically underperform compared to other pedestrian detectors. We\ndeliberately omit explicitly modelling the problem into the network (e.g. parts\nor occlusion modelling) and show that we can reach competitive performance\nwithout bells and whistles. In a wide range of experiments we analyse small and\nbig convnets, their architectural choices, parameters, and the influence of\ndifferent training data, including pre-training on surrogate tasks.\n  We present the best convnet detectors on the Caltech and KITTI dataset. On\nCaltech our convnets reach top performance both for the Caltech1x and\nCaltech10x training setup. Using additional data at training time our strongest\nconvnet model is competitive even to detectors that use additional data\n(optical flow) at test time.","url_abs":"http://arxiv.org/abs/1501.05790v1","url_pdf":"http://arxiv.org/pdf/1501.05790v1.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":"optical-flow-estimation","task_name":"Optical Flow Estimation"},{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pedestrian-detection-on-caltech","task":"Pedestrian Detection","dataset":"Caltech","model":"AlexNet","rank_in_archive_order":31,"of":33,"metrics":{"Reasonable Miss Rate":"23.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1501.05790","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}