Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890967717> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2890967717 endingPage "4027" @default.
- W2890967717 startingPage "4016" @default.
- W2890967717 abstract "We propose a method for learning landmark detectors for visual objects (such as the eyes and the nose in a face) without any manual supervision. We cast this as the problem of generating images that combine the appearance of the object as seen in a first example image with the geometry of the object as seen in a second example image, where the two examples differ by a viewpoint change and/or an object deformation. In order to factorize appearance and geometry, we introduce a tight bottleneck in the geometry-extraction process that selects and distils geometry-related features. Compared to standard image generation problems, which often use generative adversarial networks, our generation task is conditioned on both appearance and geometry and thus is significantly less ambiguous, to the point that adopting a simple perceptual loss formulation is sufficient. We demonstrate that our approach can learn object landmarks from synthetic image deformations or videos, all without manual supervision, while outperforming state-of-the-art unsupervised landmark detectors. We further show that our method is applicable to a large variety of datasets - faces, people, 3D objects, and digits - without any modifications." @default.
- W2890967717 created "2018-09-27" @default.
- W2890967717 creator A5056977175 @default.
- W2890967717 creator A5060511349 @default.
- W2890967717 creator A5082195057 @default.
- W2890967717 creator A5086192896 @default.
- W2890967717 date "2018-01-01" @default.
- W2890967717 modified "2023-09-24" @default.
- W2890967717 title "Unsupervised Learning of Object Landmarks through Conditional Image Generation" @default.
- W2890967717 hasPublicationYear "2018" @default.
- W2890967717 type Work @default.
- W2890967717 sameAs 2890967717 @default.
- W2890967717 citedByCount "83" @default.
- W2890967717 countsByYear W28909677172018 @default.
- W2890967717 countsByYear W28909677172019 @default.
- W2890967717 countsByYear W28909677172020 @default.
- W2890967717 countsByYear W28909677172021 @default.
- W2890967717 crossrefType "proceedings-article" @default.
- W2890967717 hasAuthorship W2890967717A5056977175 @default.
- W2890967717 hasAuthorship W2890967717A5060511349 @default.
- W2890967717 hasAuthorship W2890967717A5082195057 @default.
- W2890967717 hasAuthorship W2890967717A5086192896 @default.
- W2890967717 hasConcept C115961682 @default.
- W2890967717 hasConcept C131979681 @default.
- W2890967717 hasConcept C144024400 @default.
- W2890967717 hasConcept C153180895 @default.
- W2890967717 hasConcept C154945302 @default.
- W2890967717 hasConcept C167966045 @default.
- W2890967717 hasConcept C2776151529 @default.
- W2890967717 hasConcept C2779304628 @default.
- W2890967717 hasConcept C2780297707 @default.
- W2890967717 hasConcept C2781238097 @default.
- W2890967717 hasConcept C31972630 @default.
- W2890967717 hasConcept C36289849 @default.
- W2890967717 hasConcept C39890363 @default.
- W2890967717 hasConcept C41008148 @default.
- W2890967717 hasConceptScore W2890967717C115961682 @default.
- W2890967717 hasConceptScore W2890967717C131979681 @default.
- W2890967717 hasConceptScore W2890967717C144024400 @default.
- W2890967717 hasConceptScore W2890967717C153180895 @default.
- W2890967717 hasConceptScore W2890967717C154945302 @default.
- W2890967717 hasConceptScore W2890967717C167966045 @default.
- W2890967717 hasConceptScore W2890967717C2776151529 @default.
- W2890967717 hasConceptScore W2890967717C2779304628 @default.
- W2890967717 hasConceptScore W2890967717C2780297707 @default.
- W2890967717 hasConceptScore W2890967717C2781238097 @default.
- W2890967717 hasConceptScore W2890967717C31972630 @default.
- W2890967717 hasConceptScore W2890967717C36289849 @default.
- W2890967717 hasConceptScore W2890967717C39890363 @default.
- W2890967717 hasConceptScore W2890967717C41008148 @default.
- W2890967717 hasLocation W28909677171 @default.
- W2890967717 hasOpenAccess W2890967717 @default.
- W2890967717 hasPrimaryLocation W28909677171 @default.
- W2890967717 hasRelatedWork W1834627138 @default.
- W2890967717 hasRelatedWork W1901129140 @default.
- W2890967717 hasRelatedWork W1959608418 @default.
- W2890967717 hasRelatedWork W2080873731 @default.
- W2890967717 hasRelatedWork W2099471712 @default.
- W2890967717 hasRelatedWork W2194775991 @default.
- W2890967717 hasRelatedWork W2307770531 @default.
- W2890967717 hasRelatedWork W2331128040 @default.
- W2890967717 hasRelatedWork W2812468425 @default.
- W2890967717 hasRelatedWork W2949678110 @default.
- W2890967717 hasRelatedWork W2962793481 @default.
- W2890967717 hasRelatedWork W2962981304 @default.
- W2890967717 hasRelatedWork W2963045453 @default.
- W2890967717 hasRelatedWork W2963168844 @default.
- W2890967717 hasRelatedWork W2963419579 @default.
- W2890967717 hasRelatedWork W2963823554 @default.
- W2890967717 hasRelatedWork W2964121744 @default.
- W2890967717 hasRelatedWork W2971202257 @default.
- W2890967717 hasRelatedWork W2982697283 @default.
- W2890967717 hasRelatedWork W2987936369 @default.
- W2890967717 hasVolume "31" @default.
- W2890967717 isParatext "false" @default.
- W2890967717 isRetracted "false" @default.
- W2890967717 magId "2890967717" @default.
- W2890967717 workType "article" @default.