{"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/fast-gesture-recognition-with-multiple-stream","title":"Fast Gesture Recognition with Multiple Stream Discrete HMMs on 3D Skeletons","arxiv_id":"1703.02931","date":"2017-03-08","proceeding":null,"authors":["Guido Borghi","Roberto Vezzani","Rita Cucchiara"],"abstract":"HMMs are widely used in action and gesture recognition due to their\nimplementation simplicity, low computational requirement, scalability and high\nparallelism. They have worth performance even with a limited training set. All\nthese characteristics are hard to find together in other even more accurate\nmethods. In this paper, we propose a novel double-stage classification\napproach, based on Multiple Stream Discrete Hidden Markov Models (MSD-HMM) and\n3D skeleton joint data, able to reach high performances maintaining all\nadvantages listed above. The approach allows both to quickly classify\npre-segmented gestures (offline classification), and to perform temporal\nsegmentation on streams of gestures (online classification) faster than real\ntime. We test our system on three public datasets, MSRAction3D, UTKinect-Action\nand MSRDailyAction, and on a new dataset, Kinteract Dataset, explicitly created\nfor Human Computer Interaction (HCI). We obtain state of the art performances\non all of them.","url_abs":"http://arxiv.org/abs/1703.02931v1","url_pdf":"http://arxiv.org/pdf/1703.02931v1.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":[],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"gesture-recognition","task_name":"Gesture Recognition"}],"methods":[],"datasets_introduced":[{"slug":"kinteract","name":"Kinteract","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}