{"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/deep-spatial-feature-reconstruction-for","title":"Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-Free Approach","arxiv_id":"1801.00881","date":"2018-01-03","proceeding":"CVPR 2018 6","authors":["Lingxiao He","Jian Liang","Haiqing Li","Zhenan Sun"],"abstract":"Partial person re-identification (re-id) is a challenging problem, where only\nseveral partial observations (images) of people are available for matching.\nHowever, few studies have provided flexible solutions to identifying a person\nin an image containing arbitrary part of the body. In this paper, we propose a\nfast and accurate matching method to address this problem. The proposed method\nleverages Fully Convolutional Network (FCN) to generate fix-sized spatial\nfeature maps such that pixel-level features are consistent. To match a pair of\nperson images of different sizes, a novel method called Deep Spatial feature\nReconstruction (DSR) is further developed to avoid explicit alignment.\nSpecifically, DSR exploits the reconstructing error from popular dictionary\nlearning models to calculate the similarity between different spatial feature\nmaps. In that way, we expect that the proposed FCN can decrease the similarity\nof coupled images from different persons and increase that from the same\nperson. Experimental results on two partial person datasets demonstrate the\nefficiency and effectiveness of the proposed method in comparison with several\nstate-of-the-art partial person re-id approaches. Additionally, DSR achieves\ncompetitive results on a benchmark person dataset Market1501 with 83.58\\%\nRank-1 accuracy.","url_abs":"http://arxiv.org/abs/1801.00881v3","url_pdf":"http://arxiv.org/pdf/1801.00881v3.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":"deep-spatial-feature-reconstruction-for","repo_url":"https://github.com/lingxiao-he/Partial-Person-ReID","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"dictionary-learning","task_name":"Dictionary Learning"},{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[{"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1801.00881","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}