{"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/an-order-preserving-bilinear-model-for-person","title":"An Order Preserving Bilinear Model for Person Detection in Multi-Modal Data","arxiv_id":"1712.07721","date":"2017-12-20","proceeding":null,"authors":["Oytun Ulutan","Benjamin S. Riggan","Nasser M. Nasrabadi","B. S. Manjunath"],"abstract":"We propose a new order preserving bilinear framework that exploits\nlow-resolution video for person detection in a multi-modal setting using deep\nneural networks. In this setting cameras are strategically placed such that\nless robust sensors, e.g. geophones that monitor seismic activity, are located\nwithin the field of views (FOVs) of cameras. The primary challenge is being\nable to leverage sufficient information from videos where there are less than\n40 pixels on targets, while also taking advantage of less discriminative\ninformation from other modalities, e.g. seismic. Unlike state-of-the-art\nmethods, our bilinear framework retains spatio-temporal order when computing\nthe vector outer products between pairs of features. Despite the high\ndimensionality of these outer products, we demonstrate that our order\npreserving bilinear framework yields better performance than recent orderless\nbilinear models and alternative fusion methods.","url_abs":"http://arxiv.org/abs/1712.07721v2","url_pdf":"http://arxiv.org/pdf/1712.07721v2.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":"an-order-preserving-bilinear-model-for-person","repo_url":"https://github.com/oulutan/OP-Bilinear-Model","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"human-detection","task_name":"Human Detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}