{"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/future-person-localization-in-first-person","title":"Future Person Localization in First-Person Videos","arxiv_id":"1711.11217","date":"2017-11-30","proceeding":"CVPR 2018 6","authors":["Takuma Yagi","Karttikeya Mangalam","Ryo Yonetani","Yoichi Sato"],"abstract":"We present a new task that predicts future locations of people observed in\nfirst-person videos. Consider a first-person video stream continuously recorded\nby a wearable camera. Given a short clip of a person that is extracted from the\ncomplete stream, we aim to predict that person's location in future frames. To\nfacilitate this future person localization ability, we make the following three\nkey observations: a) First-person videos typically involve significant\nego-motion which greatly affects the location of the target person in future\nframes; b) Scales of the target person act as a salient cue to estimate a\nperspective effect in first-person videos; c) First-person videos often capture\npeople up-close, making it easier to leverage target poses (e.g., where they\nlook) for predicting their future locations. We incorporate these three\nobservations into a prediction framework with a multi-stream\nconvolution-deconvolution architecture. Experimental results reveal our method\nto be effective on our new dataset as well as on a public social interaction\ndataset.","url_abs":"http://arxiv.org/abs/1711.11217v2","url_pdf":"http://arxiv.org/pdf/1711.11217v2.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":"future-person-localization-in-first-person","repo_url":"https://github.com/takumayagi/fpl","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"fpl","name":"FPL","full_name":"First-Person Locomotion"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.11217","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}