Matches in SemOpenAlex for { <https://semopenalex.org/work/W2116804945> ?p ?o ?g. }
- W2116804945 endingPage "538" @default.
- W2116804945 startingPage "531" @default.
- W2116804945 abstract "In this paper we present a fully Bayesian latent variable model which exploits conditional nonlinear (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." @default.
- W2116804945 created "2016-06-24" @default.
- W2116804945 creator A5017255421 @default.
- W2116804945 creator A5022800415 @default.
- W2116804945 creator A5023849469 @default.
- W2116804945 creator A5075176672 @default.
- W2116804945 date "2012-06-26" @default.
- W2116804945 modified "2023-10-01" @default.
- W2116804945 title "Manifold Relevance Determination" @default.
- W2116804945 cites W137285897 @default.
- W2116804945 cites W1493404174 @default.
- W2116804945 cites W1541825479 @default.
- W2116804945 cites W1592111270 @default.
- W2116804945 cites W1746819321 @default.
- W2116804945 cites W194200989 @default.
- W2116804945 cites W2012725996 @default.
- W2116804945 cites W2103510282 @default.
- W2116804945 cites W2115918762 @default.
- W2116804945 cites W2123503110 @default.
- W2116804945 cites W2123921160 @default.
- W2116804945 cites W2125874614 @default.
- W2116804945 cites W2132191455 @default.
- W2116804945 cites W2136111243 @default.
- W2116804945 cites W2152829748 @default.
- W2116804945 cites W2162315509 @default.
- W2116804945 cites W2535125233 @default.
- W2116804945 cites W66306528 @default.
- W2116804945 cites W2066350599 @default.
- W2116804945 hasPublicationYear "2012" @default.
- W2116804945 type Work @default.
- W2116804945 sameAs 2116804945 @default.
- W2116804945 citedByCount "13" @default.
- W2116804945 countsByYear W21168049452013 @default.
- W2116804945 countsByYear W21168049452014 @default.
- W2116804945 countsByYear W21168049452015 @default.
- W2116804945 countsByYear W21168049452016 @default.
- W2116804945 countsByYear W21168049452018 @default.
- W2116804945 countsByYear W21168049452019 @default.
- W2116804945 crossrefType "proceedings-article" @default.
- W2116804945 hasAuthorship W2116804945A5017255421 @default.
- W2116804945 hasAuthorship W2116804945A5022800415 @default.
- W2116804945 hasAuthorship W2116804945A5023849469 @default.
- W2116804945 hasAuthorship W2116804945A5075176672 @default.
- W2116804945 hasConcept C107673813 @default.
- W2116804945 hasConcept C111030470 @default.
- W2116804945 hasConcept C111919701 @default.
- W2116804945 hasConcept C112933361 @default.
- W2116804945 hasConcept C119857082 @default.
- W2116804945 hasConcept C153180895 @default.
- W2116804945 hasConcept C154945302 @default.
- W2116804945 hasConcept C17744445 @default.
- W2116804945 hasConcept C177769412 @default.
- W2116804945 hasConcept C199539241 @default.
- W2116804945 hasConcept C2776359362 @default.
- W2116804945 hasConcept C2778572836 @default.
- W2116804945 hasConcept C41008148 @default.
- W2116804945 hasConcept C51167844 @default.
- W2116804945 hasConcept C65965080 @default.
- W2116804945 hasConcept C94625758 @default.
- W2116804945 hasConceptScore W2116804945C107673813 @default.
- W2116804945 hasConceptScore W2116804945C111030470 @default.
- W2116804945 hasConceptScore W2116804945C111919701 @default.
- W2116804945 hasConceptScore W2116804945C112933361 @default.
- W2116804945 hasConceptScore W2116804945C119857082 @default.
- W2116804945 hasConceptScore W2116804945C153180895 @default.
- W2116804945 hasConceptScore W2116804945C154945302 @default.
- W2116804945 hasConceptScore W2116804945C17744445 @default.
- W2116804945 hasConceptScore W2116804945C177769412 @default.
- W2116804945 hasConceptScore W2116804945C199539241 @default.
- W2116804945 hasConceptScore W2116804945C2776359362 @default.
- W2116804945 hasConceptScore W2116804945C2778572836 @default.
- W2116804945 hasConceptScore W2116804945C41008148 @default.
- W2116804945 hasConceptScore W2116804945C51167844 @default.
- W2116804945 hasConceptScore W2116804945C65965080 @default.
- W2116804945 hasConceptScore W2116804945C94625758 @default.
- W2116804945 hasLocation W21168049451 @default.
- W2116804945 hasOpenAccess W2116804945 @default.
- W2116804945 hasPrimaryLocation W21168049451 @default.
- W2116804945 hasRelatedWork W137285897 @default.
- W2116804945 hasRelatedWork W1493404174 @default.
- W2116804945 hasRelatedWork W1523385540 @default.
- W2116804945 hasRelatedWork W1567512734 @default.
- W2116804945 hasRelatedWork W1571870753 @default.
- W2116804945 hasRelatedWork W1663973292 @default.
- W2116804945 hasRelatedWork W1746819321 @default.
- W2116804945 hasRelatedWork W2025341678 @default.
- W2116804945 hasRelatedWork W2071207147 @default.
- W2116804945 hasRelatedWork W2103510282 @default.
- W2116804945 hasRelatedWork W2104563967 @default.
- W2116804945 hasRelatedWork W2120405375 @default.
- W2116804945 hasRelatedWork W2125027820 @default.
- W2116804945 hasRelatedWork W2132191455 @default.
- W2116804945 hasRelatedWork W2133294540 @default.
- W2116804945 hasRelatedWork W2136111243 @default.
- W2116804945 hasRelatedWork W2625683755 @default.
- W2116804945 hasRelatedWork W2951741291 @default.
- W2116804945 hasRelatedWork W2963711523 @default.
- W2116804945 hasRelatedWork W66306528 @default.