{"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/golfdb-a-video-database-for-golf-swing","title":"GolfDB: A Video Database for Golf Swing Sequencing","arxiv_id":"1903.06528","date":"2019-03-15","proceeding":null,"authors":["William McNally","Kanav Vats","Tyler Pinto","Chris Dulhanty","John McPhee","Alexander Wong"],"abstract":"The golf swing is a complex movement requiring considerable full-body\ncoordination to execute proficiently. As such, it is the subject of frequent\nscrutiny and extensive biomechanical analyses. In this paper, we introduce the\nnotion of golf swing sequencing for detecting key events in the golf swing and\nfacilitating golf swing analysis. To enable consistent evaluation of golf swing\nsequencing performance, we also introduce the benchmark database GolfDB,\nconsisting of 1400 high-quality golf swing videos, each labeled with event\nframes, bounding box, player name and sex, club type, and view type.\nFurthermore, to act as a reference baseline for evaluating golf swing\nsequencing performance on GolfDB, we propose a lightweight deep neural network\ncalled SwingNet, which possesses a hybrid deep convolutional and recurrent\nneural network architecture. SwingNet correctly detects eight golf swing events\nat an average rate of 76.1%, and six out of eight events at a rate of 91.8%. In\nline with the proposed baseline SwingNet, we advocate the use of\ncomputationally efficient models in future research to promote in-the-field\nanalysis via deployment on readily-available mobile devices.","url_abs":"http://arxiv.org/abs/1903.06528v1","url_pdf":"http://arxiv.org/pdf/1903.06528v1.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":"golfdb-a-video-database-for-golf-swing","repo_url":"https://github.com/wmcnally/GolfDB","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[{"slug":"golfdb","name":"GolfDB","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1903.06528","atlas_url":"https://app.syntology.ai/?focus=1903.06528","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}