Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089691176> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3089691176 endingPage "211" @default.
- W3089691176 startingPage "202" @default.
- W3089691176 abstract "Transformation-based methods for shape analysis offer a consistent framework to model the geometrical content of images. Most often relying on diffeomorphic transforms, they lack however the ability to properly handle texture and differing topological content. Conversely, modern deep learning methods offer a very efficient way to analyze image textures. Building on the theory of metamorphoses, which models images as combined intensity-domain and spatial-domain transforms of a prototype, we introduce the “metamorphic” auto-encoding architecture. This class of neural networks is interpreted as a Bayesian generative and hierarchical model, allowing the joint estimation of the network parameters, a representative prototype of the training images, as well as the relative importance between the geometrical and texture contents.We give arguments for the practical relevance of the learned prototype and Euclidean latent-space metric, achieved thanks to an explicit normalization layer. Finally, the ability of the proposed architecture to learn joint and relevant shape and appearance representations from image collections is illustrated on BraTs 2018 datasets, showing in particular an encouraging step towards personalized numerical simulation of tumors with data-driven models." @default.
- W3089691176 created "2020-10-08" @default.
- W3089691176 creator A5005778444 @default.
- W3089691176 creator A5030817992 @default.
- W3089691176 creator A5058667353 @default.
- W3089691176 creator A5080254367 @default.
- W3089691176 date "2020-01-01" @default.
- W3089691176 modified "2023-10-09" @default.
- W3089691176 title "Learning Joint Shape and Appearance Representations with Metamorphic Auto-Encoders" @default.
- W3089691176 cites W1579576867 @default.
- W3089691176 cites W1641498739 @default.
- W3089691176 cites W1969002377 @default.
- W3089691176 cites W2074745044 @default.
- W3089691176 cites W2089940272 @default.
- W3089691176 cites W2141125852 @default.
- W3089691176 cites W2176287621 @default.
- W3089691176 cites W2412479940 @default.
- W3089691176 cites W2751069891 @default.
- W3089691176 cites W2798896071 @default.
- W3089691176 cites W2799913653 @default.
- W3089691176 cites W2807725536 @default.
- W3089691176 cites W2883105610 @default.
- W3089691176 cites W2904555209 @default.
- W3089691176 cites W2914320392 @default.
- W3089691176 cites W2919115771 @default.
- W3089691176 cites W2945049370 @default.
- W3089691176 cites W4206566734 @default.
- W3089691176 cites W813277965 @default.
- W3089691176 doi "https://doi.org/10.1007/978-3-030-59710-8_20" @default.
- W3089691176 hasPublicationYear "2020" @default.
- W3089691176 type Work @default.
- W3089691176 sameAs 3089691176 @default.
- W3089691176 citedByCount "4" @default.
- W3089691176 countsByYear W30896911762022 @default.
- W3089691176 countsByYear W30896911762023 @default.
- W3089691176 crossrefType "book-chapter" @default.
- W3089691176 hasAuthorship W3089691176A5005778444 @default.
- W3089691176 hasAuthorship W3089691176A5030817992 @default.
- W3089691176 hasAuthorship W3089691176A5058667353 @default.
- W3089691176 hasAuthorship W3089691176A5080254367 @default.
- W3089691176 hasBestOaLocation W30896911762 @default.
- W3089691176 hasConcept C108583219 @default.
- W3089691176 hasConcept C11413529 @default.
- W3089691176 hasConcept C129782007 @default.
- W3089691176 hasConcept C134306372 @default.
- W3089691176 hasConcept C136886441 @default.
- W3089691176 hasConcept C144024400 @default.
- W3089691176 hasConcept C153180895 @default.
- W3089691176 hasConcept C154945302 @default.
- W3089691176 hasConcept C19165224 @default.
- W3089691176 hasConcept C2524010 @default.
- W3089691176 hasConcept C31972630 @default.
- W3089691176 hasConcept C33923547 @default.
- W3089691176 hasConcept C36503486 @default.
- W3089691176 hasConcept C41008148 @default.
- W3089691176 hasConceptScore W3089691176C108583219 @default.
- W3089691176 hasConceptScore W3089691176C11413529 @default.
- W3089691176 hasConceptScore W3089691176C129782007 @default.
- W3089691176 hasConceptScore W3089691176C134306372 @default.
- W3089691176 hasConceptScore W3089691176C136886441 @default.
- W3089691176 hasConceptScore W3089691176C144024400 @default.
- W3089691176 hasConceptScore W3089691176C153180895 @default.
- W3089691176 hasConceptScore W3089691176C154945302 @default.
- W3089691176 hasConceptScore W3089691176C19165224 @default.
- W3089691176 hasConceptScore W3089691176C2524010 @default.
- W3089691176 hasConceptScore W3089691176C31972630 @default.
- W3089691176 hasConceptScore W3089691176C33923547 @default.
- W3089691176 hasConceptScore W3089691176C36503486 @default.
- W3089691176 hasConceptScore W3089691176C41008148 @default.
- W3089691176 hasLocation W30896911761 @default.
- W3089691176 hasLocation W30896911762 @default.
- W3089691176 hasLocation W30896911763 @default.
- W3089691176 hasLocation W30896911764 @default.
- W3089691176 hasOpenAccess W3089691176 @default.
- W3089691176 hasPrimaryLocation W30896911761 @default.
- W3089691176 hasRelatedWork W2359348847 @default.
- W3089691176 hasRelatedWork W2591697403 @default.
- W3089691176 hasRelatedWork W2904022177 @default.
- W3089691176 hasRelatedWork W2904857019 @default.
- W3089691176 hasRelatedWork W2944728705 @default.
- W3089691176 hasRelatedWork W2953716828 @default.
- W3089691176 hasRelatedWork W3011538607 @default.
- W3089691176 hasRelatedWork W4294432981 @default.
- W3089691176 hasRelatedWork W4321276295 @default.
- W3089691176 hasRelatedWork W4321441197 @default.
- W3089691176 isParatext "false" @default.
- W3089691176 isRetracted "false" @default.
- W3089691176 magId "3089691176" @default.
- W3089691176 workType "book-chapter" @default.