Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Manifold relevance determination
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP.
2012 (engelsk)Inngår i: Proceedings of the 29th International Conference on Machine Learning, ICML 2012, 2012, s. 145-152Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

In this paper we present a fully Bayesian latent variable model which exploits conditional non-linear (in)-dependence structures to learn an efficient latent representation. The latent space is factorized to represent shared and private information from multiple views of the data. In contrast to previous approaches, we introduce a relaxation to the discrete segmentation and allow for a "softly" shared latent space. Further, Bayesian techniques allow us to automatically estimate the dimensionality of the latent spaces. The model is capable of capturing structure underlying extremely high dimensional spaces. This is illustrated by modelling unprocessed images with tenths of thousands of pixels. This also allows us to directly generate novel images from the trained model by sampling from the discovered latent spaces. We also demonstrate the model by prediction of human pose in an ambiguous setting. Our Bayesian framework allows us to perform disambiguation in a principled manner by including latent space priors which incorporate the dynamic nature of the data.

sted, utgiver, år, opplag, sider
2012. s. 145-152
Emneord [en]
Bayesian frameworks, Bayesian techniques, Dynamic nature, High dimensional spaces, Human pose, Latent variable models, Multiple views, Private information, Artificial intelligence, Software engineering, Learning systems
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-105438Scopus ID: 2-s2.0-84867113123ISBN: 978-145031285-1 (tryckt)OAI: oai:DiVA.org:kth-105438DiVA, id: diva2:571285
Konferanse
29th International Conference on Machine Learning, ICML 2012, 26 June 2012 through 1 July 2012, Edinburgh
Merknad

QC 20121122

Tilgjengelig fra: 2012-11-22 Laget: 2012-11-21 Sist oppdatert: 2018-01-12bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Scopus

Søk i DiVA

Av forfatter/redaktør
Ek, Carl Henrik
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetric

isbn
urn-nbn
Totalt: 56 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf