{"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/jointly-attentive-spatial-temporal-pooling","title":"Jointly Attentive Spatial-Temporal Pooling Networks for Video-based Person Re-Identification","arxiv_id":"1708.02286","date":"2017-08-03","proceeding":"ICCV 2017 10","authors":["Shuangjie Xu","Yu Cheng","Kang Gu","Yang Yang","Shiyu Chang","Pan Zhou"],"abstract":"Person Re-Identification (person re-id) is a crucial task as its applications\nin visual surveillance and human-computer interaction. In this work, we present\na novel joint Spatial and Temporal Attention Pooling Network (ASTPN) for\nvideo-based person re-identification, which enables the feature extractor to be\naware of the current input video sequences, in a way that interdependency from\nthe matching items can directly influence the computation of each other's\nrepresentation. Specifically, the spatial pooling layer is able to select\nregions from each frame, while the attention temporal pooling performed can\nselect informative frames over the sequence, both pooling guided by the\ninformation from distance matching. Experiments are conduced on the iLIDS-VID,\nPRID-2011 and MARS datasets and the results demonstrate that this approach\noutperforms existing state-of-art methods. We also analyze how the joint\npooling in both dimensions can boost the person re-id performance more\neffectively than using either of them separately.","url_abs":"http://arxiv.org/abs/1708.02286v2","url_pdf":"http://arxiv.org/pdf/1708.02286v2.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":"jointly-attentive-spatial-temporal-pooling","repo_url":"https://github.com/shuangjiexu/Spatial-Temporal-Pooling-Networks-ReID","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"torch","reach":{"status":"unanswered"}}],"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":"https://app.syntology.ai/?focus=1708.02286","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}