FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2979346253> ?p ?o ?g. }

• W2979346253 abstract "In this work, we consider the problem of learning a hierarchical generative model of an object from a set of images which show examples of the object in the presence of variable background clutter. Existing approaches to this problem are limited by making strong a-priori assumptions about the object’s geometric structure and require seg- mented training data for learning. In this paper, we propose a novel framework for learning hierarchical compositional models (HCMs) which do not suffer from the mentioned limitations. We present a generalized formulation of HCMs and describe a greedy structure learning framework that consists of two phases: Bottom-up part learning and top-down model composition. Our framework integrates the foreground-background segmentation problem into the structure learning task via a background model. As a result, we can jointly optimize for the number of layers in the hierarchy, the number of parts per layer and a foreground- background segmentation based on class labels only. We show that the learned HCMs are semantically meaningful and achieve competitive results when compared to other generative object models at object classification on a standard transfer learning dataset." @default.
• W2979346253 created "2019-10-18" @default.
• W2979346253 creator A5017215421 @default.
• W2979346253 creator A5025828990 @default.
• W2979346253 creator A5035132507 @default.
• W2979346253 creator A5038895545 @default.
• W2979346253 creator A5052211172 @default.
• W2979346253 creator A5060935547 @default.
• W2979346253 creator A5067014251 @default.
• W2979346253 creator A5084928022 @default.
• W2979346253 date "2019-06-01" @default.
• W2979346253 modified "2023-09-25" @default.
• W2979346253 title "Greedy Structure Learning of Hierarchical Compositional Models" @default.
• W2979346253 cites W1151768060 @default.
• W2979346253 cites W1722318740 @default.
• W2979346253 cites W1821057786 @default.
• W2979346253 cites W1965080940 @default.
• W2979346253 cites W1985967702 @default.
• W2979346253 cites W2030536784 @default.
• W2979346253 cites W2038952578 @default.
• W2979346253 cites W2041240878 @default.
• W2979346253 cites W2079930597 @default.
• W2979346253 cites W2089779414 @default.
• W2979346253 cites W2104095591 @default.
• W2979346253 cites W2125802042 @default.
• W2979346253 cites W2126747264 @default.
• W2979346253 cites W2128053425 @default.
• W2979346253 cites W2136922672 @default.
• W2979346253 cites W2143299724 @default.
• W2979346253 cites W2145169631 @default.
• W2979346253 cites W2145743319 @default.
• W2979346253 cites W2149466042 @default.
• W2979346253 cites W2151693816 @default.
• W2979346253 cites W2157785665 @default.
• W2979346253 cites W2160547390 @default.
• W2979346253 cites W2162915993 @default.
• W2979346253 cites W2237250383 @default.
• W2979346253 cites W2613282858 @default.
• W2979346253 cites W2765332150 @default.
• W2979346253 cites W3169507310 @default.
• W2979346253 cites W328593463 @default.
• W2979346253 cites W4205969993 @default.
• W2979346253 cites W4319782616 @default.
• W2979346253 doi "https://doi.org/10.1109/cvpr.2019.01188" @default.
• W2979346253 hasPublicationYear "2019" @default.
• W2979346253 type Work @default.
• W2979346253 sameAs 2979346253 @default.
• W2979346253 citedByCount "3" @default.
• W2979346253 countsByYear W29793462532020 @default.
• W2979346253 countsByYear W29793462532021 @default.
• W2979346253 crossrefType "proceedings-article" @default.
• W2979346253 hasAuthorship W2979346253A5017215421 @default.
• W2979346253 hasAuthorship W2979346253A5025828990 @default.
• W2979346253 hasAuthorship W2979346253A5035132507 @default.
• W2979346253 hasAuthorship W2979346253A5038895545 @default.
• W2979346253 hasAuthorship W2979346253A5052211172 @default.
• W2979346253 hasAuthorship W2979346253A5060935547 @default.
• W2979346253 hasAuthorship W2979346253A5067014251 @default.
• W2979346253 hasAuthorship W2979346253A5084928022 @default.
• W2979346253 hasBestOaLocation W29793462532 @default.
• W2979346253 hasConcept C111472728 @default.
• W2979346253 hasConcept C119857082 @default.
• W2979346253 hasConcept C132094186 @default.
• W2979346253 hasConcept C138885662 @default.
• W2979346253 hasConcept C153180895 @default.
• W2979346253 hasConcept C154945302 @default.
• W2979346253 hasConcept C162324750 @default.
• W2979346253 hasConcept C167966045 @default.
• W2979346253 hasConcept C177264268 @default.
• W2979346253 hasConcept C199360897 @default.
• W2979346253 hasConcept C2781238097 @default.
• W2979346253 hasConcept C2781289151 @default.
• W2979346253 hasConcept C31170391 @default.
• W2979346253 hasConcept C34447519 @default.
• W2979346253 hasConcept C39890363 @default.
• W2979346253 hasConcept C41008148 @default.
• W2979346253 hasConcept C554190296 @default.
• W2979346253 hasConcept C73752529 @default.
• W2979346253 hasConcept C75553542 @default.
• W2979346253 hasConcept C76155785 @default.
• W2979346253 hasConcept C89600930 @default.
• W2979346253 hasConceptScore W2979346253C111472728 @default.
• W2979346253 hasConceptScore W2979346253C119857082 @default.
• W2979346253 hasConceptScore W2979346253C132094186 @default.
• W2979346253 hasConceptScore W2979346253C138885662 @default.
• W2979346253 hasConceptScore W2979346253C153180895 @default.
• W2979346253 hasConceptScore W2979346253C154945302 @default.
• W2979346253 hasConceptScore W2979346253C162324750 @default.
• W2979346253 hasConceptScore W2979346253C167966045 @default.
• W2979346253 hasConceptScore W2979346253C177264268 @default.
• W2979346253 hasConceptScore W2979346253C199360897 @default.
• W2979346253 hasConceptScore W2979346253C2781238097 @default.
• W2979346253 hasConceptScore W2979346253C2781289151 @default.
• W2979346253 hasConceptScore W2979346253C31170391 @default.
• W2979346253 hasConceptScore W2979346253C34447519 @default.
• W2979346253 hasConceptScore W2979346253C39890363 @default.
• W2979346253 hasConceptScore W2979346253C41008148 @default.
• W2979346253 hasConceptScore W2979346253C554190296 @default.
• W2979346253 hasConceptScore W2979346253C73752529 @default.
• W2979346253 hasConceptScore W2979346253C75553542 @default.

• next