{"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/learning-to-recognize-touch-gestures","title":"Learning to recognize touch gestures: recurrent vs. convolutional features and dynamic sampling","arxiv_id":"1802.09901","date":"2018-02-19","proceeding":null,"authors":["Quentin Debard","Christian Wolf","Stéphane Canu","Julien Arné"],"abstract":"We propose a fully automatic method for learning gestures on big touch\ndevices in a potentially multi-user context. The goal is to learn general\nmodels capable of adapting to different gestures, user styles and hardware\nvariations (e.g. device sizes, sampling frequencies and regularities).\n  Based on deep neural networks, our method features a novel dynamic sampling\nand temporal normalization component, transforming variable length gestures\ninto fixed length representations while preserving finger/surface contact\ntransitions, that is, the topology of the signal. This sequential\nrepresentation is then processed with a convolutional model capable, unlike\nrecurrent networks, of learning hierarchical representations with different\nlevels of abstraction.\n  To demonstrate the interest of the proposed method, we introduce a new touch\ngestures dataset with 6591 gestures performed by 27 people, which is, up to our\nknowledge, the first of its kind: a publicly available multi-touch gesture\ndataset for interaction.\n  We also tested our method on a standard dataset of symbolic touch gesture\nrecognition, the MMG dataset, outperforming the state of the art and reporting\nclose to perfect performance.","url_abs":"http://arxiv.org/abs/1802.09901v1","url_pdf":"http://arxiv.org/pdf/1802.09901v1.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":"learning-to-recognize-touch-gestures","repo_url":"https://github.com/chriswegmann/drone_steering","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"gesture-recognition","task_name":"Gesture Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}