Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Ergebnis 12 von 144
IEEE transactions on pattern analysis and machine intelligence, 2017-10, Vol.39 (10), p.1973-1984
2017
Volltextzugriff (PDF)

Details

Autor(en) / Beteiligte
Titel
Learning to Recognize Human Activities Using Soft Labels
Ist Teil von
  • IEEE transactions on pattern analysis and machine intelligence, 2017-10, Vol.39 (10), p.1973-1984
Ort / Verlag
United States: IEEE
Erscheinungsjahr
2017
Quelle
IEEE Electronic Library Online
Beschreibungen/Notizen
  • Human activity recognition system is of great importance in robot-care scenarios. Typically, training such a system requires activity labels to be both completely and accurately annotated. In this paper, we go beyond such restriction and propose a learning method that allow labels to be incomplete and uncertain. We introduce the idea of soft labels which allows annotators to assign multiple, and weighted labels to data segments. This is very useful in many situations, e.g., when the labels are uncertain, when part of the labels are missing, or when multiple annotators assign inconsistent labels. We formulate the activity recognition task as a sequential labeling problem. Latent variables are embedded in the model in order to exploit sub-level semantics for better estimation. We propose a max-margin framework which incorporate soft labels for learning the model parameters. The model is evaluated on two challenging datasets. To simulate the uncertainty in data annotation, we randomly change the labels for transition segments. The results show significant improvement over the state-of-the-art approach.
Sprache
Englisch
Identifikatoren
ISSN: 0162-8828
eISSN: 1939-3539, 2160-9292
DOI: 10.1109/TPAMI.2016.2621761
Titel-ID: cdi_proquest_miscellaneous_1861612775

Weiterführende Literatur

Empfehlungen zum selben Thema automatisch vorgeschlagen von bX