{"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/end-to-end-deep-kronecker-product-matching","title":"End-to-End Deep Kronecker-Product Matching for Person Re-identification","arxiv_id":"1807.11182","date":"2018-07-30","proceeding":"CVPR 2018 6","authors":["Yantao Shen","Tong Xiao","Hongsheng Li","Shuai Yi","Xiaogang Wang"],"abstract":"Person re-identification aims to robustly measure similarities between person\nimages. The significant variation of person poses and viewing angles challenges\nfor accurate person re-identification. The spatial layout and correspondences\nbetween query person images are vital information for tackling this problem but\nare ignored by most state-of-the-art methods. In this paper, we propose a novel\nKronecker Product Matching module to match feature maps of different persons in\nan end-to-end trainable deep neural network. A novel feature soft warping\nscheme is designed for aligning the feature maps based on matching results,\nwhich is shown to be crucial for achieving superior accuracy. The multi-scale\nfeatures based on hourglass-like networks and self-residual attention are also\nexploited to further boost the re-identification performance. The proposed\napproach outperforms state-of-the-art methods on the Market-1501, CUHK03, and\nDukeMTMC datasets, which demonstrates the effectiveness and generalization\nability of our proposed approach.","url_abs":"http://arxiv.org/abs/1807.11182v1","url_pdf":"http://arxiv.org/pdf/1807.11182v1.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":"end-to-end-deep-kronecker-product-matching","repo_url":"https://github.com/YantaoShen/kpm_rw_person_reid","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"end-to-end-deep-kronecker-product-matching","repo_url":"https://github.com/MindSpore-scientific-2/code-12/tree/main/Kronecker-Attention-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1807.11182","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}