{"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/part-level-convolutional-neural-networks-for","title":"Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment","arxiv_id":"1810.00689","date":"2018-10-01","proceeding":null,"authors":["Inyong Yun","Cheolkon Jung","Xinran Wang","Alfred O. Hero","Joongkyu Kim"],"abstract":"Pedestrians in videos have a wide range of appearances such as body poses,\nocclusions, and complex backgrounds, and there exists the proposal shift\nproblem in pedestrian detection that causes the loss of body parts such as head\nand legs. To address it, we propose part-level convolutional neural networks\n(CNN) for pedestrian detection using saliency and boundary box alignment in\nthis paper. The proposed network consists of two sub-networks: detection and\nalignment. We use saliency in the detection sub-network to remove false\npositives such as lamp posts and trees. We adopt bounding box alignment on\ndetection proposals in the alignment sub-network to address the proposal shift\nproblem. First, we combine FCN and CAM to extract deep features for pedestrian\ndetection. Then, we perform part-level CNN to recall the lost body parts.\nExperimental results on various datasets demonstrate that the proposed method\nremarkably improves accuracy in pedestrian detection and outperforms existing\nstate-of-the-arts in terms of log average miss rate at false position per image\n(FPPI).","url_abs":"http://arxiv.org/abs/1810.00689v1","url_pdf":"http://arxiv.org/pdf/1810.00689v1.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":"part-level-convolutional-neural-networks-for","repo_url":"https://github.com/iyyun/Part-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"pedestrian-detection","task_name":"Pedestrian Detection"}],"methods":[{"method_slug":"cam","method_name":"CAM"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fcn","method_name":"FCN"},{"method_slug":"max-pooling","method_name":"Max Pooling"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/pedestrian-detection-on-caltech","task":"Pedestrian Detection","dataset":"Caltech","model":"Part-level CNN + saliency and bounding box alignment","rank_in_archive_order":27,"of":33,"metrics":{"Reasonable Miss Rate":"12.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}