{"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/revisiting-hand-crafted-feature-for-action","title":"Revisiting hand-crafted feature for action recognition: a set of improved dense trajectories","arxiv_id":"1711.10143","date":"2017-11-28","proceeding":null,"authors":["Kenji Matsui","Toru Tamaki","Gwladys Auffret","Bisser Raytchev","Kazufumi Kaneda"],"abstract":"We propose a feature for action recognition called Trajectory-Set (TS), on\ntop of the improved Dense Trajectory (iDT). The TS feature encodes only\ntrajectories around densely sampled interest points, without any appearance\nfeatures. Experimental results on the UCF50, UCF101, and HMDB51 action datasets\ndemonstrate that TS is comparable to state-of-the-arts, and outperforms many\nother methods; for HMDB the accuracy of 85.4%, compared to the best accuracy of\n80.2% obtained by a deep method. Our code is available on-line at\nhttps://github.com/Gauffret/TrajectorySet .","url_abs":"http://arxiv.org/abs/1711.10143v1","url_pdf":"http://arxiv.org/pdf/1711.10143v1.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":"revisiting-hand-crafted-feature-for-action","repo_url":"https://github.com/Gauffret/TrajectorySet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"action-recognition-in-videos","task_name":"Action Recognition"},{"task_slug":"action-recognition","task_name":"Temporal Action Localization"}],"methods":[{"method_slug":"ts","method_name":"TS"}],"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}