An adversarial framework for op en-set human action recognition using skeleton data

Basit Öğe Kaydı
dc.contributor.authorOztimur Karadag, Ozge
dc.date.accessioned2026-01-24T12:26:38Z
dc.date.available2026-01-24T12:26:38Z
dc.date.issued2021
dc.departmentAlanya Alaaddin Keykubat Üniversitesi
dc.description.abstractHuman action recognition is a fundamental problem which is applied in various domains, and it is widely studied in the literature. Majority of the studies model action recognition as a closed-set problem. However, in real-life applications it usually arises as an op en-set problem where a set of actions are not available during training but are introduced to the system during testing. In this study, we propose an op en-set action recognition system, human action recognition and novel action detection system (HARNAD), which consists of two stages and uses only 3D skeleton information. In the first stage, HARNAD recognizes a given action and in the second stage it decides whether the action really belongs to one of the a priori known classes or if it is a novel action. We evaluate the performance of the system experimentally both in terms of recognition and novelty detection. We also compare the system performance with state-of-the-art op en-set recognition methods. Our experiments show that HARNAD is compatible with state-of-the-art methods in novelty detection, while it is superior to those methods in recognition.
dc.identifier.doi10.3906/elk-2003-124
dc.identifier.endpage729
dc.identifier.issn1300-0632
dc.identifier.issn1303-6203
dc.identifier.issue2
dc.identifier.scopus2-s2.0-85104752671
dc.identifier.scopusqualityQ3
dc.identifier.startpage717
dc.identifier.trdizinid514920
dc.identifier.urihttps://doi.org/10.3906/elk-2003-124
dc.identifier.urihttps://search.trdizin.gov.tr/tr/yayin/detay/514920
dc.identifier.urihttps://hdl.handle.net/20.500.12868/4823
dc.identifier.volume29
dc.identifier.wosWOS:000680005700004
dc.identifier.wosqualityQ4
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakTR-Dizin
dc.language.isoen
dc.publisherTubitak Scientific & Technological Research Council Turkey
dc.relation.ispartofTurkish Journal of Electrical Engineering and Computer Sciences
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WoS_20260121
dc.subjecten-set recognition
dc.subjectnovelty detection
dc.subjecthuman action recognition
dc.subjectadversarial networks
dc.titleAn adversarial framework for op en-set human action recognition using skeleton data
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
TR-Dizin İndeksli Yayınlar Koleksiyonu