Matches in SemOpenAlex for { <https://semopenalex.org/work/W3083619744> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3083619744 abstract "In deep representational learning, it is often desired to isolate a particular factor (termed {em content}) from other factors (referred to as {em style}). What constitutes the content is typically specified by users through explicit labels in the data, while all unlabeled/unknown factors are regarded as style. Recently, it has been shown that such content-labeled data can be effectively exploited by modifying the deep latent factor models (e.g., VAE) such that the style and content are well separated in the latent representations. However, the approach assumes that the content factor is categorical-valued (e.g., subject ID in face image data, or digit class in the MNIST dataset). In certain situations, the content is ordinal-valued, that is, the values the content factor takes are {em ordered} rather than categorical, making content-labeled VAEs, including the latent space they infer, suboptimal. In this paper, we propose a novel extension of VAE that imposes a partially ordered set (poset) structure in the content latent space, while simultaneously making it aligned with the ordinal content values. To this end, instead of the iid Gaussian latent prior adopted in prior approaches, we introduce a conditional Gaussian spacing prior model. This model admits a tractable joint Gaussian prior, but also effectively places negligible density values on the content latent configurations that violate the poset constraint. To evaluate this model, we consider two specific ordinal structured problems: estimating a subject's age in a face image and elucidating the calorie amount in a food meal image. We demonstrate significant improvements in content-style separation over previous non-ordinal approaches." @default.
- W3083619744 created "2020-09-11" @default.
- W3083619744 creator A5020368096 @default.
- W3083619744 creator A5034892664 @default.
- W3083619744 date "2020-09-07" @default.
- W3083619744 modified "2023-10-16" @default.
- W3083619744 title "Ordinal-Content VAE: Isolating Ordinal-Valued Content Factors in Deep Latent Variable Models" @default.
- W3083619744 cites W1691728462 @default.
- W3083619744 cites W1959608418 @default.
- W3083619744 cites W2157617585 @default.
- W3083619744 cites W2163922914 @default.
- W3083619744 cites W2188956040 @default.
- W3083619744 cites W2239239723 @default.
- W3083619744 cites W2281112906 @default.
- W3083619744 cites W2510725918 @default.
- W3083619744 cites W2559823555 @default.
- W3083619744 cites W2753738274 @default.
- W3083619744 cites W2766527109 @default.
- W3083619744 cites W2785902771 @default.
- W3083619744 cites W2897959392 @default.
- W3083619744 cites W2904054107 @default.
- W3083619744 cites W2950662112 @default.
- W3083619744 cites W2962818303 @default.
- W3083619744 cites W2963104724 @default.
- W3083619744 cites W2963226019 @default.
- W3083619744 cites W2963504544 @default.
- W3083619744 cites W2964127395 @default.
- W3083619744 cites W2964208960 @default.
- W3083619744 cites W2980118882 @default.
- W3083619744 cites W2996554397 @default.
- W3083619744 hasPublicationYear "2020" @default.
- W3083619744 type Work @default.
- W3083619744 sameAs 3083619744 @default.
- W3083619744 citedByCount "0" @default.
- W3083619744 crossrefType "posted-content" @default.
- W3083619744 hasAuthorship W3083619744A5020368096 @default.
- W3083619744 hasAuthorship W3083619744A5034892664 @default.
- W3083619744 hasConcept C10879293 @default.
- W3083619744 hasConcept C119857082 @default.
- W3083619744 hasConcept C121332964 @default.
- W3083619744 hasConcept C134306372 @default.
- W3083619744 hasConcept C153180895 @default.
- W3083619744 hasConcept C154945302 @default.
- W3083619744 hasConcept C163716315 @default.
- W3083619744 hasConcept C177264268 @default.
- W3083619744 hasConcept C199360897 @default.
- W3083619744 hasConcept C2778152352 @default.
- W3083619744 hasConcept C33923547 @default.
- W3083619744 hasConcept C41008148 @default.
- W3083619744 hasConcept C51167844 @default.
- W3083619744 hasConcept C5274069 @default.
- W3083619744 hasConcept C62520636 @default.
- W3083619744 hasConcept C85461838 @default.
- W3083619744 hasConceptScore W3083619744C10879293 @default.
- W3083619744 hasConceptScore W3083619744C119857082 @default.
- W3083619744 hasConceptScore W3083619744C121332964 @default.
- W3083619744 hasConceptScore W3083619744C134306372 @default.
- W3083619744 hasConceptScore W3083619744C153180895 @default.
- W3083619744 hasConceptScore W3083619744C154945302 @default.
- W3083619744 hasConceptScore W3083619744C163716315 @default.
- W3083619744 hasConceptScore W3083619744C177264268 @default.
- W3083619744 hasConceptScore W3083619744C199360897 @default.
- W3083619744 hasConceptScore W3083619744C2778152352 @default.
- W3083619744 hasConceptScore W3083619744C33923547 @default.
- W3083619744 hasConceptScore W3083619744C41008148 @default.
- W3083619744 hasConceptScore W3083619744C51167844 @default.
- W3083619744 hasConceptScore W3083619744C5274069 @default.
- W3083619744 hasConceptScore W3083619744C62520636 @default.
- W3083619744 hasConceptScore W3083619744C85461838 @default.
- W3083619744 hasLocation W30836197441 @default.
- W3083619744 hasOpenAccess W3083619744 @default.
- W3083619744 hasPrimaryLocation W30836197441 @default.
- W3083619744 hasRelatedWork W1507153853 @default.
- W3083619744 hasRelatedWork W1512656208 @default.
- W3083619744 hasRelatedWork W1520417700 @default.
- W3083619744 hasRelatedWork W158520387 @default.
- W3083619744 hasRelatedWork W1606081677 @default.
- W3083619744 hasRelatedWork W1914255464 @default.
- W3083619744 hasRelatedWork W2144832675 @default.
- W3083619744 hasRelatedWork W2153412625 @default.
- W3083619744 hasRelatedWork W2161246474 @default.
- W3083619744 hasRelatedWork W2290335729 @default.
- W3083619744 hasRelatedWork W2760947890 @default.
- W3083619744 hasRelatedWork W2885007608 @default.
- W3083619744 hasRelatedWork W2950594207 @default.
- W3083619744 hasRelatedWork W2951166049 @default.
- W3083619744 hasRelatedWork W2952602938 @default.
- W3083619744 hasRelatedWork W2963987720 @default.
- W3083619744 hasRelatedWork W2988503392 @default.
- W3083619744 hasRelatedWork W3016398456 @default.
- W3083619744 hasRelatedWork W3177430934 @default.
- W3083619744 hasRelatedWork W781385459 @default.
- W3083619744 isParatext "false" @default.
- W3083619744 isRetracted "false" @default.
- W3083619744 magId "3083619744" @default.
- W3083619744 workType "article" @default.