Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Efficient Non-linear Markov Models for Human Motion

Lehrmann, A., Gehler, P., & Nowozin, S. (2014). Efficient Non-linear Markov Models for Human Motion. In 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014) (978-1-4799-5117-8, pp. 1314-1321). Los Alamitos, CA: IEEE Computer Society. doi:10.1109/CVPR.2014.171.

Item is

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Lehrmann, Andreas1, Autor           
Gehler, Peter1, Autor           
Nowozin, Sebastian2, Autor           
Affiliations:
1Dept. Perceiving Systems, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497642              
2Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Inhalt

einblenden:
ausblenden:
Schlagwörter: Abt. Black; Abt. Schölkopf
 Zusammenfassung: Dynamic Bayesian networks such as Hidden Markov Models (HMMs) are successfully used as probabilistic models for human motion. The use of hidden variables makes them expressive models, but inference is only approximate and requires procedures such as particle filters or Markov chain Monte Carlo methods. In this work we propose to instead use simple Markov models that only model observed quantities. We retain a highly expressive dynamic model by using interactions that are nonlinear and non-parametric. A presentation of our approach in terms of latent variables shows logarithmic growth for the computation of exact loglikelihoods in the number of latent states. We validate our model on human motion capture data and demonstrate state-of-the-art performance on action recognition and motion completion tasks.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2014-06
 Publikationsstatus: Online veröffentlicht
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: lehrmann14motion
DOI: 10.1109/CVPR.2014.171
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014)
Veranstaltungsort: Columbus, Ohio
Start-/Enddatum: 2014-06-23 - 2014-06-28

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2014)
  Untertitel : Proceedings
  Alternativer Titel :
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Los Alamitos, CA : IEEE Computer Society, 978-1-4799-5117-8
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1314 - 1321 Identifikator: -