Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949678110> ?p ?o ?g. }
- W2949678110 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.
- W2949678110 created "2019-06-27" @default.
- W2949678110 creator A5056977175 @default.
- W2949678110 creator A5060511349 @default.
- W2949678110 creator A5082195057 @default.
- W2949678110 creator A5086192896 @default.
- W2949678110 date "2018-06-20" @default.
- W2949678110 modified "2023-09-27" @default.
- W2949678110 title "Unsupervised Learning of Object Landmarks through Conditional Image Generation" @default.
- W2949678110 cites W1445015017 @default.
- W2949678110 cites W1522301498 @default.
- W2949678110 cites W1686810756 @default.
- W2949678110 cites W1795776638 @default.
- W2949678110 cites W1834627138 @default.
- W2949678110 cites W1896424170 @default.
- W2949678110 cites W1976948919 @default.
- W2949678110 cites W2011700682 @default.
- W2949678110 cites W2012885984 @default.
- W2949678110 cites W2025768430 @default.
- W2949678110 cites W2064675550 @default.
- W2949678110 cites W2099471712 @default.
- W2949678110 cites W2100495367 @default.
- W2949678110 cites W2101032778 @default.
- W2949678110 cites W2111372597 @default.
- W2949678110 cites W2134557905 @default.
- W2949678110 cites W2135341757 @default.
- W2949678110 cites W2136922672 @default.
- W2949678110 cites W2175030374 @default.
- W2949678110 cites W2184218725 @default.
- W2949678110 cites W2281112906 @default.
- W2949678110 cites W2331128040 @default.
- W2949678110 cites W2335728318 @default.
- W2949678110 cites W2403878043 @default.
- W2949678110 cites W2418098761 @default.
- W2949678110 cites W2434741482 @default.
- W2949678110 cites W2470475590 @default.
- W2949678110 cites W2475287302 @default.
- W2949678110 cites W2557449848 @default.
- W2949678110 cites W2607738331 @default.
- W2949678110 cites W2611103765 @default.
- W2949678110 cites W2619034550 @default.
- W2949678110 cites W2807725536 @default.
- W2949678110 cites W2808631503 @default.
- W2949678110 cites W2887997593 @default.
- W2949678110 cites W2949099979 @default.
- W2949678110 cites W2950064337 @default.
- W2949678110 cites W2951004968 @default.
- W2949678110 cites W2951707615 @default.
- W2949678110 cites W2952069407 @default.
- W2949678110 cites W2952434594 @default.
- W2949678110 cites W2952453038 @default.
- W2949678110 cites W2953382498 @default.
- W2949678110 cites W2963073614 @default.
- W2949678110 cites W2963174698 @default.
- W2949678110 cites W2963419579 @default.
- W2949678110 cites W2963470893 @default.
- W2949678110 hasPublicationYear "2018" @default.
- W2949678110 type Work @default.
- W2949678110 sameAs 2949678110 @default.
- W2949678110 citedByCount "17" @default.
- W2949678110 countsByYear W29496781102018 @default.
- W2949678110 countsByYear W29496781102019 @default.
- W2949678110 countsByYear W29496781102020 @default.
- W2949678110 countsByYear W29496781102021 @default.
- W2949678110 crossrefType "posted-content" @default.
- W2949678110 hasAuthorship W2949678110A5056977175 @default.
- W2949678110 hasAuthorship W2949678110A5060511349 @default.
- W2949678110 hasAuthorship W2949678110A5082195057 @default.
- W2949678110 hasAuthorship W2949678110A5086192896 @default.
- W2949678110 hasConcept C115961682 @default.
- W2949678110 hasConcept C131979681 @default.
- W2949678110 hasConcept C144024400 @default.
- W2949678110 hasConcept C153180895 @default.
- W2949678110 hasConcept C154945302 @default.
- W2949678110 hasConcept C167966045 @default.
- W2949678110 hasConcept C2524010 @default.
- W2949678110 hasConcept C2776151529 @default.
- W2949678110 hasConcept C2779304628 @default.
- W2949678110 hasConcept C2780297707 @default.
- W2949678110 hasConcept C2781238097 @default.
- W2949678110 hasConcept C28719098 @default.
- W2949678110 hasConcept C31972630 @default.
- W2949678110 hasConcept C33923547 @default.
- W2949678110 hasConcept C36289849 @default.
- W2949678110 hasConcept C39890363 @default.
- W2949678110 hasConcept C41008148 @default.
- W2949678110 hasConceptScore W2949678110C115961682 @default.
- W2949678110 hasConceptScore W2949678110C131979681 @default.
- W2949678110 hasConceptScore W2949678110C144024400 @default.
- W2949678110 hasConceptScore W2949678110C153180895 @default.
- W2949678110 hasConceptScore W2949678110C154945302 @default.
- W2949678110 hasConceptScore W2949678110C167966045 @default.
- W2949678110 hasConceptScore W2949678110C2524010 @default.
- W2949678110 hasConceptScore W2949678110C2776151529 @default.
- W2949678110 hasConceptScore W2949678110C2779304628 @default.
- W2949678110 hasConceptScore W2949678110C2780297707 @default.
- W2949678110 hasConceptScore W2949678110C2781238097 @default.
- W2949678110 hasConceptScore W2949678110C28719098 @default.
- W2949678110 hasConceptScore W2949678110C31972630 @default.
- W2949678110 hasConceptScore W2949678110C33923547 @default.