Matches in SemOpenAlex for { <https://semopenalex.org/work/W3119841092> ?p ?o ?g. }
- W3119841092 abstract "We consider the novel task of learning disentangled representations of object shape and appearance across multiple domains (e.g., dogs and cars). The goal is to learn a generative model that learns an intermediate distribution, which borrows a subset of properties from each domain, enabling the generation of images that did not exist in any domain exclusively. This challenging problem requires an accurate disentanglement of object shape, appearance, and background from each domain, so that the appearance and shape factors from the two domains can be interchanged. We augment an existing approach that can disentangle factors within a single domain but struggles to do so across domains. Our key technical contribution is to represent object appearance with a differentiable histogram of visual features, and to optimize the generator so that two images with the same latent appearance factor but different latent shape factors produce similar histograms. On multiple multi-domain datasets, we demonstrate our method leads to accurate and consistent appearance and shape transfer across domains." @default.
- W3119841092 created "2021-01-18" @default.
- W3119841092 creator A5030649976 @default.
- W3119841092 creator A5045669078 @default.
- W3119841092 creator A5082091356 @default.
- W3119841092 date "2021-05-03" @default.
- W3119841092 modified "2023-09-24" @default.
- W3119841092 title "Generating Furry Cars: Disentangling Object Shape and Appearance across Multiple Domains" @default.
- W3119841092 cites W1484228140 @default.
- W3119841092 cites W1797268635 @default.
- W3119841092 cites W1861492603 @default.
- W3119841092 cites W1924619199 @default.
- W3119841092 cites W1959608418 @default.
- W3119841092 cites W2099471712 @default.
- W3119841092 cites W2108598243 @default.
- W3119841092 cites W2138011018 @default.
- W3119841092 cites W2138621090 @default.
- W3119841092 cites W2144742590 @default.
- W3119841092 cites W2194321275 @default.
- W3119841092 cites W2331128040 @default.
- W3119841092 cites W2434741482 @default.
- W3119841092 cites W2603777577 @default.
- W3119841092 cites W2630837129 @default.
- W3119841092 cites W2753738274 @default.
- W3119841092 cites W2766091292 @default.
- W3119841092 cites W2771558241 @default.
- W3119841092 cites W2798404873 @default.
- W3119841092 cites W2807725536 @default.
- W3119841092 cites W2893749619 @default.
- W3119841092 cites W2903141607 @default.
- W3119841092 cites W2942626212 @default.
- W3119841092 cites W2951939904 @default.
- W3119841092 cites W2962770929 @default.
- W3119841092 cites W2962793481 @default.
- W3119841092 cites W2962935987 @default.
- W3119841092 cites W2963045453 @default.
- W3119841092 cites W2963129901 @default.
- W3119841092 cites W2963684088 @default.
- W3119841092 cites W2963890275 @default.
- W3119841092 cites W2963896050 @default.
- W3119841092 cites W2964168187 @default.
- W3119841092 cites W2971155163 @default.
- W3119841092 cites W3005680577 @default.
- W3119841092 cites W3034600949 @default.
- W3119841092 cites W3035149916 @default.
- W3119841092 cites W3035258717 @default.
- W3119841092 cites W3159890710 @default.
- W3119841092 hasPublicationYear "2021" @default.
- W3119841092 type Work @default.
- W3119841092 sameAs 3119841092 @default.
- W3119841092 citedByCount "1" @default.
- W3119841092 countsByYear W31198410922021 @default.
- W3119841092 crossrefType "proceedings-article" @default.
- W3119841092 hasAuthorship W3119841092A5030649976 @default.
- W3119841092 hasAuthorship W3119841092A5045669078 @default.
- W3119841092 hasAuthorship W3119841092A5082091356 @default.
- W3119841092 hasConcept C115961682 @default.
- W3119841092 hasConcept C121332964 @default.
- W3119841092 hasConcept C129641003 @default.
- W3119841092 hasConcept C134306372 @default.
- W3119841092 hasConcept C153180895 @default.
- W3119841092 hasConcept C154945302 @default.
- W3119841092 hasConcept C163258240 @default.
- W3119841092 hasConcept C167966045 @default.
- W3119841092 hasConcept C202615002 @default.
- W3119841092 hasConcept C26517878 @default.
- W3119841092 hasConcept C2780992000 @default.
- W3119841092 hasConcept C2781238097 @default.
- W3119841092 hasConcept C31972630 @default.
- W3119841092 hasConcept C33923547 @default.
- W3119841092 hasConcept C36503486 @default.
- W3119841092 hasConcept C38652104 @default.
- W3119841092 hasConcept C39890363 @default.
- W3119841092 hasConcept C41008148 @default.
- W3119841092 hasConcept C53533937 @default.
- W3119841092 hasConcept C62520636 @default.
- W3119841092 hasConcept C83248878 @default.
- W3119841092 hasConcept C89600930 @default.
- W3119841092 hasConceptScore W3119841092C115961682 @default.
- W3119841092 hasConceptScore W3119841092C121332964 @default.
- W3119841092 hasConceptScore W3119841092C129641003 @default.
- W3119841092 hasConceptScore W3119841092C134306372 @default.
- W3119841092 hasConceptScore W3119841092C153180895 @default.
- W3119841092 hasConceptScore W3119841092C154945302 @default.
- W3119841092 hasConceptScore W3119841092C163258240 @default.
- W3119841092 hasConceptScore W3119841092C167966045 @default.
- W3119841092 hasConceptScore W3119841092C202615002 @default.
- W3119841092 hasConceptScore W3119841092C26517878 @default.
- W3119841092 hasConceptScore W3119841092C2780992000 @default.
- W3119841092 hasConceptScore W3119841092C2781238097 @default.
- W3119841092 hasConceptScore W3119841092C31972630 @default.
- W3119841092 hasConceptScore W3119841092C33923547 @default.
- W3119841092 hasConceptScore W3119841092C36503486 @default.
- W3119841092 hasConceptScore W3119841092C38652104 @default.
- W3119841092 hasConceptScore W3119841092C39890363 @default.
- W3119841092 hasConceptScore W3119841092C41008148 @default.
- W3119841092 hasConceptScore W3119841092C53533937 @default.
- W3119841092 hasConceptScore W3119841092C62520636 @default.
- W3119841092 hasConceptScore W3119841092C83248878 @default.
- W3119841092 hasConceptScore W3119841092C89600930 @default.