{"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/personnet-person-re-identification-with-deep","title":"PersonNet: Person Re-identification with Deep Convolutional Neural Networks","arxiv_id":"1601.07255","date":"2016-01-27","proceeding":null,"authors":["Lin Wu","Chunhua Shen","Anton Van Den Hengel"],"abstract":"In this paper, we propose a deep end-to-end neu- ral network to\nsimultaneously learn high-level features and a corresponding similarity metric\nfor person re-identification. The network takes a pair of raw RGB images as\ninput, and outputs a similarity value indicating whether the two input images\ndepict the same person. A layer of computing neighborhood range differences\nacross two input images is employed to capture local relationship between\npatches. This operation is to seek a robust feature from input images. By\nincreasing the depth to 10 weight layers and using very small (3$\\times$3)\nconvolution filters, our architecture achieves a remarkable improvement on the\nprior-art configurations. Meanwhile, an adaptive Root- Mean-Square (RMSProp)\ngradient decent algorithm is integrated into our architecture, which is\nbeneficial to deep nets. Our method consistently outperforms state-of-the-art\non two large datasets (CUHK03 and Market-1501), and a medium-sized data set\n(CUHK01).","url_abs":"http://arxiv.org/abs/1601.07255v2","url_pdf":"http://arxiv.org/pdf/1601.07255v2.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":"personnet-person-re-identification-with-deep","repo_url":"https://github.com/leonardovlibido/PersonRe-Identification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1601.07255","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}