Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226520161> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4226520161 abstract "Deep neural networks have been used widely to learn the latent structure of datasets, across modalities such as images, shapes, and audio signals. However, existing models are generally modality-dependent, requiring custom architectures and objectives to process different classes of signals. We leverage neural fields to capture the underlying structure in image, shape, audio and cross-modal audiovisual domains in a modality-independent manner. We cast our task as one of learning a manifold, where we aim to infer a low-dimensional, locally linear subspace in which our data resides. By enforcing coverage of the manifold, local linearity, and local isometry, our model -- dubbed GEM -- learns to capture the underlying structure of datasets across modalities. We can then travel along linear regions of our manifold to obtain perceptually consistent interpolations between samples, and can further use GEM to recover points on our manifold and glean not only diverse completions of input images, but cross-modal hallucinations of audio or image signals. Finally, we show that by walking across the underlying manifold of GEM, we may generate new samples in our signal domains. Code and additional results are available at https://yilundu.github.io/gem/." @default.
- W4226520161 created "2022-05-05" @default.
- W4226520161 creator A5016061808 @default.
- W4226520161 creator A5024828997 @default.
- W4226520161 creator A5067388487 @default.
- W4226520161 creator A5071093940 @default.
- W4226520161 date "2021-11-11" @default.
- W4226520161 modified "2023-09-23" @default.
- W4226520161 title "Learning Signal-Agnostic Manifolds of Neural Fields" @default.
- W4226520161 doi "https://doi.org/10.48550/arxiv.2111.06387" @default.
- W4226520161 hasPublicationYear "2021" @default.
- W4226520161 type Work @default.
- W4226520161 citedByCount "0" @default.
- W4226520161 crossrefType "posted-content" @default.
- W4226520161 hasAuthorship W4226520161A5016061808 @default.
- W4226520161 hasAuthorship W4226520161A5024828997 @default.
- W4226520161 hasAuthorship W4226520161A5067388487 @default.
- W4226520161 hasAuthorship W4226520161A5071093940 @default.
- W4226520161 hasBestOaLocation W42265201611 @default.
- W4226520161 hasConcept C127413603 @default.
- W4226520161 hasConcept C151876577 @default.
- W4226520161 hasConcept C153083717 @default.
- W4226520161 hasConcept C153120616 @default.
- W4226520161 hasConcept C153180895 @default.
- W4226520161 hasConcept C154945302 @default.
- W4226520161 hasConcept C177264268 @default.
- W4226520161 hasConcept C185592680 @default.
- W4226520161 hasConcept C188027245 @default.
- W4226520161 hasConcept C199360897 @default.
- W4226520161 hasConcept C2776760102 @default.
- W4226520161 hasConcept C2779843651 @default.
- W4226520161 hasConcept C2780226545 @default.
- W4226520161 hasConcept C32834561 @default.
- W4226520161 hasConcept C41008148 @default.
- W4226520161 hasConcept C50644808 @default.
- W4226520161 hasConcept C529865628 @default.
- W4226520161 hasConcept C70518039 @default.
- W4226520161 hasConcept C71139939 @default.
- W4226520161 hasConcept C78519656 @default.
- W4226520161 hasConceptScore W4226520161C127413603 @default.
- W4226520161 hasConceptScore W4226520161C151876577 @default.
- W4226520161 hasConceptScore W4226520161C153083717 @default.
- W4226520161 hasConceptScore W4226520161C153120616 @default.
- W4226520161 hasConceptScore W4226520161C153180895 @default.
- W4226520161 hasConceptScore W4226520161C154945302 @default.
- W4226520161 hasConceptScore W4226520161C177264268 @default.
- W4226520161 hasConceptScore W4226520161C185592680 @default.
- W4226520161 hasConceptScore W4226520161C188027245 @default.
- W4226520161 hasConceptScore W4226520161C199360897 @default.
- W4226520161 hasConceptScore W4226520161C2776760102 @default.
- W4226520161 hasConceptScore W4226520161C2779843651 @default.
- W4226520161 hasConceptScore W4226520161C2780226545 @default.
- W4226520161 hasConceptScore W4226520161C32834561 @default.
- W4226520161 hasConceptScore W4226520161C41008148 @default.
- W4226520161 hasConceptScore W4226520161C50644808 @default.
- W4226520161 hasConceptScore W4226520161C529865628 @default.
- W4226520161 hasConceptScore W4226520161C70518039 @default.
- W4226520161 hasConceptScore W4226520161C71139939 @default.
- W4226520161 hasConceptScore W4226520161C78519656 @default.
- W4226520161 hasLocation W42265201611 @default.
- W4226520161 hasOpenAccess W4226520161 @default.
- W4226520161 hasPrimaryLocation W42265201611 @default.
- W4226520161 hasRelatedWork W1488410531 @default.
- W4226520161 hasRelatedWork W1528356187 @default.
- W4226520161 hasRelatedWork W155079911 @default.
- W4226520161 hasRelatedWork W198500362 @default.
- W4226520161 hasRelatedWork W2039101446 @default.
- W4226520161 hasRelatedWork W2112684860 @default.
- W4226520161 hasRelatedWork W2370200218 @default.
- W4226520161 hasRelatedWork W3105934373 @default.
- W4226520161 hasRelatedWork W4297833440 @default.
- W4226520161 hasRelatedWork W4307864332 @default.
- W4226520161 isParatext "false" @default.
- W4226520161 isRetracted "false" @default.
- W4226520161 workType "article" @default.