Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385453669> ?p ?o ?g. }
- W4385453669 endingPage "4500" @default.
- W4385453669 startingPage "4486" @default.
- W4385453669 abstract "Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables and these models use a non-linear function (generator) to map latent samples into the data space. On the other hand, the non-linearity of the generator implies that the latent space shows an unsatisfactory projection of the data space, which results in poor representation learning. This weak projection, however, can be addressed by a Riemannian metric, and we show that geodesics computation and accurate interpolations between data samples on the Riemannian manifold can substantially improve the performance of deep generative models. In this paper, a Variational spatial-Transformer AutoEncoder (VTAE) is proposed to minimize geodesics on a Riemannian manifold and improve representation learning. In particular, we carefully design the variational autoencoder with an encoded spatial-Transformer to explicitly expand the latent variable model to data on a Riemannian manifold, and obtain global context modelling. Moreover, to have smooth and plausible interpolations while traversing between two different objects' latent representations, we propose a geodesic interpolation network different from the existing models that use linear interpolation with inferior performance. Experiments on benchmarks show that our proposed model can improve predictive accuracy and versatility over a range of computer vision tasks, including image interpolations, and reconstructions." @default.
- W4385453669 created "2023-08-02" @default.
- W4385453669 creator A5001819736 @default.
- W4385453669 creator A5009550171 @default.
- W4385453669 creator A5066119228 @default.
- W4385453669 creator A5079232252 @default.
- W4385453669 creator A5083774648 @default.
- W4385453669 date "2023-01-01" @default.
- W4385453669 modified "2023-10-16" @default.
- W4385453669 title "VTAE: Variational Transformer Autoencoder with Manifolds Learning" @default.
- W4385453669 cites W1540288699 @default.
- W4385453669 cites W2036996178 @default.
- W4385453669 cites W2053186076 @default.
- W4385453669 cites W2086920314 @default.
- W4385453669 cites W2102166818 @default.
- W4385453669 cites W2112796928 @default.
- W4385453669 cites W2177899970 @default.
- W4385453669 cites W2601564443 @default.
- W4385453669 cites W2732026016 @default.
- W4385453669 cites W2953421261 @default.
- W4385453669 cites W2964082390 @default.
- W4385453669 cites W2972632651 @default.
- W4385453669 cites W2981352086 @default.
- W4385453669 cites W3043547428 @default.
- W4385453669 cites W3049651907 @default.
- W4385453669 cites W3134430547 @default.
- W4385453669 cites W3136958399 @default.
- W4385453669 cites W3149124402 @default.
- W4385453669 cites W3199003182 @default.
- W4385453669 cites W3199920114 @default.
- W4385453669 cites W3200296481 @default.
- W4385453669 cites W4206441147 @default.
- W4385453669 cites W4229081350 @default.
- W4385453669 cites W4280607744 @default.
- W4385453669 cites W4312290517 @default.
- W4385453669 cites W4312291121 @default.
- W4385453669 cites W4312567873 @default.
- W4385453669 cites W4312771828 @default.
- W4385453669 cites W4312947743 @default.
- W4385453669 doi "https://doi.org/10.1109/tip.2023.3299495" @default.
- W4385453669 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37527317" @default.
- W4385453669 hasPublicationYear "2023" @default.
- W4385453669 type Work @default.
- W4385453669 citedByCount "1" @default.
- W4385453669 countsByYear W43854536692023 @default.
- W4385453669 crossrefType "journal-article" @default.
- W4385453669 hasAuthorship W4385453669A5001819736 @default.
- W4385453669 hasAuthorship W4385453669A5009550171 @default.
- W4385453669 hasAuthorship W4385453669A5066119228 @default.
- W4385453669 hasAuthorship W4385453669A5079232252 @default.
- W4385453669 hasAuthorship W4385453669A5083774648 @default.
- W4385453669 hasBestOaLocation W43854536692 @default.
- W4385453669 hasConcept C101738243 @default.
- W4385453669 hasConcept C108583219 @default.
- W4385453669 hasConcept C11413529 @default.
- W4385453669 hasConcept C115961682 @default.
- W4385453669 hasConcept C127413603 @default.
- W4385453669 hasConcept C134306372 @default.
- W4385453669 hasConcept C137800194 @default.
- W4385453669 hasConcept C151876577 @default.
- W4385453669 hasConcept C153120616 @default.
- W4385453669 hasConcept C153180895 @default.
- W4385453669 hasConcept C154945302 @default.
- W4385453669 hasConcept C165818556 @default.
- W4385453669 hasConcept C2779593128 @default.
- W4385453669 hasConcept C33923547 @default.
- W4385453669 hasConcept C41008148 @default.
- W4385453669 hasConcept C51167844 @default.
- W4385453669 hasConcept C529865628 @default.
- W4385453669 hasConcept C70518039 @default.
- W4385453669 hasConcept C78519656 @default.
- W4385453669 hasConceptScore W4385453669C101738243 @default.
- W4385453669 hasConceptScore W4385453669C108583219 @default.
- W4385453669 hasConceptScore W4385453669C11413529 @default.
- W4385453669 hasConceptScore W4385453669C115961682 @default.
- W4385453669 hasConceptScore W4385453669C127413603 @default.
- W4385453669 hasConceptScore W4385453669C134306372 @default.
- W4385453669 hasConceptScore W4385453669C137800194 @default.
- W4385453669 hasConceptScore W4385453669C151876577 @default.
- W4385453669 hasConceptScore W4385453669C153120616 @default.
- W4385453669 hasConceptScore W4385453669C153180895 @default.
- W4385453669 hasConceptScore W4385453669C154945302 @default.
- W4385453669 hasConceptScore W4385453669C165818556 @default.
- W4385453669 hasConceptScore W4385453669C2779593128 @default.
- W4385453669 hasConceptScore W4385453669C33923547 @default.
- W4385453669 hasConceptScore W4385453669C41008148 @default.
- W4385453669 hasConceptScore W4385453669C51167844 @default.
- W4385453669 hasConceptScore W4385453669C529865628 @default.
- W4385453669 hasConceptScore W4385453669C70518039 @default.
- W4385453669 hasConceptScore W4385453669C78519656 @default.
- W4385453669 hasLocation W43854536691 @default.
- W4385453669 hasLocation W43854536692 @default.
- W4385453669 hasLocation W43854536693 @default.
- W4385453669 hasOpenAccess W4385453669 @default.
- W4385453669 hasPrimaryLocation W43854536691 @default.
- W4385453669 hasRelatedWork W1559692913 @default.
- W4385453669 hasRelatedWork W1969803895 @default.
- W4385453669 hasRelatedWork W2355395139 @default.