{"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/anticipating-daily-intention-using-on-wrist","title":"Anticipating Daily Intention using On-Wrist Motion Triggered Sensing","arxiv_id":"1710.07477","date":"2017-10-20","proceeding":"ICCV 2017 10","authors":["Tz-Ying Wu","Ting-An Chien","Cheng-Sheng Chan","Chan-Wei Hu","Min Sun"],"abstract":"Anticipating human intention by observing one's actions has many\napplications. For instance, picking up a cellphone, then a charger (actions)\nimplies that one wants to charge the cellphone (intention). By anticipating the\nintention, an intelligent system can guide the user to the closest power\noutlet. We propose an on-wrist motion triggered sensing system for anticipating\ndaily intentions, where the on-wrist sensors help us to persistently observe\none's actions. The core of the system is a novel Recurrent Neural Network (RNN)\nand Policy Network (PN), where the RNN encodes visual and motion observation to\nanticipate intention, and the PN parsimoniously triggers the process of visual\nobservation to reduce computation requirement. We jointly trained the whole\nnetwork using policy gradient and cross-entropy loss. To evaluate, we collect\nthe first daily \"intention\" dataset consisting of 2379 videos with 34\nintentions and 164 unique action sequences. Our method achieves 92.68%, 90.85%,\n97.56% accuracy on three users while processing only 29% of the visual\nobservation on average.","url_abs":"http://arxiv.org/abs/1710.07477v1","url_pdf":"http://arxiv.org/pdf/1710.07477v1.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":"anticipating-daily-intention-using-on-wrist","repo_url":"https://github.com/gina9726/Intent-Anticipate","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[],"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}