Matches in SemOpenAlex for { <https://semopenalex.org/work/W2079789819> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2079789819 abstract "Recognizing objects in fine-grained domains can be extremely challenging due to the subtle differences between subcategories. Discriminative markings are often highly localized, leading traditional object recognition approaches to struggle with the large pose variation often present in these domains. Pose-normalization seeks to align training exemplars, either piecewise by part or globally for the whole object, effectively factoring out differences in pose and in viewing angle. Prior approaches relied on computationally-expensive filter ensembles for part localization and required extensive supervision. This paper proposes two pose-normalized descriptors based on computationally-efficient deformable part models. The first leverages the semantics inherent in strongly-supervised DPM parts. The second exploits weak semantic annotations to learn cross-component correspondences, computing pose-normalized descriptors from the latent parts of a weakly-supervised DPM. These representations enable pooling across pose and viewpoint, in turn facilitating tasks such as fine-grained recognition and attribute prediction. Experiments conducted on the Caltech-UCSD Birds 200 dataset and Berkeley Human Attribute dataset demonstrate significant improvements of our approach over state-of-art algorithms." @default.
- W2079789819 created "2016-06-24" @default.
- W2079789819 creator A5029105520 @default.
- W2079789819 creator A5031485831 @default.
- W2079789819 creator A5050729131 @default.
- W2079789819 creator A5063552773 @default.
- W2079789819 date "2013-12-01" @default.
- W2079789819 modified "2023-09-25" @default.
- W2079789819 title "Deformable Part Descriptors for Fine-Grained Recognition and Attribute Prediction" @default.
- W2079789819 cites W1989684337 @default.
- W2079789819 cites W1993149133 @default.
- W2079789819 cites W1994213117 @default.
- W2079789819 cites W1994529670 @default.
- W2079789819 cites W2031489346 @default.
- W2079789819 cites W2032558548 @default.
- W2079789819 cites W2039507552 @default.
- W2079789819 cites W2045750950 @default.
- W2079789819 cites W2045798786 @default.
- W2079789819 cites W2091759811 @default.
- W2079789819 cites W2098411764 @default.
- W2079789819 cites W2101722384 @default.
- W2079789819 cites W2110015572 @default.
- W2079789819 cites W2110765924 @default.
- W2079789819 cites W2118696714 @default.
- W2079789819 cites W2122686738 @default.
- W2079789819 cites W2124351162 @default.
- W2079789819 cites W2128560777 @default.
- W2079789819 cites W2129492014 @default.
- W2079789819 cites W2150856297 @default.
- W2079789819 cites W2152923755 @default.
- W2079789819 cites W2168356304 @default.
- W2079789819 cites W2294130536 @default.
- W2079789819 cites W2533598788 @default.
- W2079789819 cites W2536626143 @default.
- W2079789819 cites W3143107425 @default.
- W2079789819 doi "https://doi.org/10.1109/iccv.2013.96" @default.
- W2079789819 hasPublicationYear "2013" @default.
- W2079789819 type Work @default.
- W2079789819 sameAs 2079789819 @default.
- W2079789819 citedByCount "170" @default.
- W2079789819 countsByYear W20797898192013 @default.
- W2079789819 countsByYear W20797898192014 @default.
- W2079789819 countsByYear W20797898192015 @default.
- W2079789819 countsByYear W20797898192016 @default.
- W2079789819 countsByYear W20797898192017 @default.
- W2079789819 countsByYear W20797898192018 @default.
- W2079789819 countsByYear W20797898192019 @default.
- W2079789819 countsByYear W20797898192020 @default.
- W2079789819 countsByYear W20797898192021 @default.
- W2079789819 countsByYear W20797898192022 @default.
- W2079789819 countsByYear W20797898192023 @default.
- W2079789819 crossrefType "proceedings-article" @default.
- W2079789819 hasAuthorship W2079789819A5029105520 @default.
- W2079789819 hasAuthorship W2079789819A5031485831 @default.
- W2079789819 hasAuthorship W2079789819A5050729131 @default.
- W2079789819 hasAuthorship W2079789819A5063552773 @default.
- W2079789819 hasConcept C119857082 @default.
- W2079789819 hasConcept C136886441 @default.
- W2079789819 hasConcept C144024400 @default.
- W2079789819 hasConcept C153180895 @default.
- W2079789819 hasConcept C154945302 @default.
- W2079789819 hasConcept C184337299 @default.
- W2079789819 hasConcept C19165224 @default.
- W2079789819 hasConcept C199360897 @default.
- W2079789819 hasConcept C41008148 @default.
- W2079789819 hasConcept C70437156 @default.
- W2079789819 hasConcept C97931131 @default.
- W2079789819 hasConceptScore W2079789819C119857082 @default.
- W2079789819 hasConceptScore W2079789819C136886441 @default.
- W2079789819 hasConceptScore W2079789819C144024400 @default.
- W2079789819 hasConceptScore W2079789819C153180895 @default.
- W2079789819 hasConceptScore W2079789819C154945302 @default.
- W2079789819 hasConceptScore W2079789819C184337299 @default.
- W2079789819 hasConceptScore W2079789819C19165224 @default.
- W2079789819 hasConceptScore W2079789819C199360897 @default.
- W2079789819 hasConceptScore W2079789819C41008148 @default.
- W2079789819 hasConceptScore W2079789819C70437156 @default.
- W2079789819 hasConceptScore W2079789819C97931131 @default.
- W2079789819 hasLocation W20797898191 @default.
- W2079789819 hasOpenAccess W2079789819 @default.
- W2079789819 hasPrimaryLocation W20797898191 @default.
- W2079789819 hasRelatedWork W1617617605 @default.
- W2079789819 hasRelatedWork W2016839265 @default.
- W2079789819 hasRelatedWork W2024160000 @default.
- W2079789819 hasRelatedWork W2043075591 @default.
- W2079789819 hasRelatedWork W2061273563 @default.
- W2079789819 hasRelatedWork W2285052147 @default.
- W2079789819 hasRelatedWork W2729514902 @default.
- W2079789819 hasRelatedWork W2773500201 @default.
- W2079789819 hasRelatedWork W2921836287 @default.
- W2079789819 hasRelatedWork W4287995534 @default.
- W2079789819 isParatext "false" @default.
- W2079789819 isRetracted "false" @default.
- W2079789819 magId "2079789819" @default.
- W2079789819 workType "article" @default.