{"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/video-based-person-re-identification-using","title":"Video-based Person Re-identification Using Spatial-Temporal Attention Networks","arxiv_id":"1810.11261","date":"2018-10-26","proceeding":null,"authors":["Shivansh Rao","Tanzila Rahman","Mrigank Rochan","Yang Wang"],"abstract":"We consider the problem of video-based person re-identification. The goal is\nto identify a person from videos captured under different cameras. In this\npaper, we propose an efficient spatial-temporal attention based model for\nperson re-identification from videos. Our method generates an attention score\nfor each frame based on frame-level features. The attention scores of all\nframes in a video are used to produce a weighted feature vector for the input\nvideo. Unlike most existing deep learning methods that use global\nrepresentation, our approach focuses on attention scores. Extensive experiments\non two benchmark datasets demonstrate that our method achieves the\nstate-of-the-art performance. This is a technical report.","url_abs":"http://arxiv.org/abs/1810.11261v1","url_pdf":"http://arxiv.org/pdf/1810.11261v1.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":"video-based-person-re-identification-using","repo_url":"https://github.com/rshivansh/Spatial-Temporal-attention","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"person-re-identification","task_name":"Person Re-Identification"},{"task_slug":"video-based-person-re-identification","task_name":"Video-Based Person Re-Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}