An adversarial framework for open-set human action recognition using skeleton data
| dc.contributor.author | Karadag, Ozge Oztımur | |
| dc.date.accessioned | 2026-01-24T12:01:29Z | |
| dc.date.available | 2026-01-24T12:01:29Z | |
| dc.date.issued | 2021 | |
| dc.department | Alanya Alaaddin Keykubat Üniversitesi | |
| dc.description.abstract | Human action recognition is a fundamental problem which is applied in various domains, and it is widely\rstudied in the literature. Majority of the studies model action recognition as a closed-set problem. However, in real-\rlife applications it usually arises as an open-set problem where a set of actions are not available during training but\rare introduced to the system during testing. In this study, we propose an open-set action recognition system, human\raction recognition and novel action detection system (HARNAD), which consists of two stages and uses only 3D skeleton\rinformation. In the first stage, HARNAD recognizes a given action and in the second stage it decides whether the\raction really belongs to one of the a priori known classes or if it is a novel action. We evaluate the performance of the\rsystem experimentally both in terms of recognition and novelty detection. We also compare the system performance with\rstate-of-the-art open-set recognition methods. Our experiments show that HARNAD is compatible with state-of-the-art\rmethods in novelty detection, while it is superior to those methods in recognition | |
| dc.identifier.doi | 10.3906/elk-2003-124 | |
| dc.identifier.endpage | 729 | |
| dc.identifier.issn | 1300-0632 | |
| dc.identifier.issue | 2 | |
| dc.identifier.startpage | 717 | |
| dc.identifier.trdizinid | 514920 | |
| dc.identifier.uri | https://search.trdizin.gov.tr/tr/yayin/detay/514920 | |
| dc.identifier.uri | https://doi.org/10.3906/elk-2003-124 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12868/4376 | |
| dc.identifier.volume | 29 | |
| dc.indekslendigikaynak | TR-Dizin | |
| dc.language.iso | en | |
| dc.relation.ispartof | Turkish Journal of Electrical Engineering and Computer Sciences | |
| dc.relation.publicationcategory | Makale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanı | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.snmz | KA_TR-Dizin_20260121 | |
| dc.subject | Bilgisayar Bilimleri | |
| dc.subject | Yazılım Mühendisliği | |
| dc.title | An adversarial framework for open-set human action recognition using skeleton data | |
| dc.type | Article |
