Matches in SemOpenAlex for { <https://semopenalex.org/work/W1995766682> ?p ?o ?g. }
- W1995766682 endingPage "73" @default.
- W1995766682 startingPage "56" @default.
- W1995766682 abstract "To learn semantic attributes, existing methods typically train one discriminative model for each word in a vocabulary of nameable properties. However, this “one model per word” assumption is problematic: while a word might have a precise linguistic definition, it need not have a precise visual definition. We propose to discover shades of attribute meaning. Given an attribute name, we use crowdsourced image labels to discover the latent factors underlying how different annotators perceive the named concept. We show that structure in those latent factors helps reveal shades, that is, interpretations for the attribute shared by some group of annotators. Using these shades, we train classifiers to capture the primary (often subtle) variants of the attribute. The resulting models are both semantic and visually precise. By catering to users’ interpretations, they improve attribute prediction accuracy on novel images. Shades also enable more successful attribute-based image search, by providing robust personalized models for retrieving multi-attribute query results. They are widely applicable to tasks that involve describing visual content, such as zero-shot category learning and organization of photo collections." @default.
- W1995766682 created "2016-06-24" @default.
- W1995766682 creator A5012765543 @default.
- W1995766682 creator A5072882318 @default.
- W1995766682 date "2015-01-23" @default.
- W1995766682 modified "2023-09-25" @default.
- W1995766682 title "Discovering Attribute Shades of Meaning with the Crowd" @default.
- W1995766682 cites W1500188831 @default.
- W1995766682 cites W1500937733 @default.
- W1995766682 cites W1508851371 @default.
- W1995766682 cites W1528802670 @default.
- W1995766682 cites W1597421340 @default.
- W1995766682 cites W1822439997 @default.
- W1995766682 cites W1942126453 @default.
- W1995766682 cites W1953590900 @default.
- W1995766682 cites W1987971958 @default.
- W1995766682 cites W2018006179 @default.
- W1995766682 cites W2047956997 @default.
- W1995766682 cites W2070148066 @default.
- W1995766682 cites W2080171500 @default.
- W1995766682 cites W2084435358 @default.
- W1995766682 cites W2085040216 @default.
- W1995766682 cites W2085660690 @default.
- W1995766682 cites W2088227600 @default.
- W1995766682 cites W2091759811 @default.
- W1995766682 cites W2097053051 @default.
- W1995766682 cites W2098411764 @default.
- W1995766682 cites W2102497689 @default.
- W1995766682 cites W2102985109 @default.
- W1995766682 cites W2103490241 @default.
- W1995766682 cites W2112053844 @default.
- W1995766682 cites W2118341388 @default.
- W1995766682 cites W2123053055 @default.
- W1995766682 cites W2125323310 @default.
- W1995766682 cites W2126448884 @default.
- W1995766682 cites W2139185560 @default.
- W1995766682 cites W2147152072 @default.
- W1995766682 cites W2156843740 @default.
- W1995766682 cites W2157032868 @default.
- W1995766682 cites W2163708240 @default.
- W1995766682 cites W2165318118 @default.
- W1995766682 cites W2166354010 @default.
- W1995766682 cites W2294130536 @default.
- W1995766682 cites W2404962578 @default.
- W1995766682 cites W3143107425 @default.
- W1995766682 cites W4233983496 @default.
- W1995766682 cites W4234035084 @default.
- W1995766682 cites W48884151 @default.
- W1995766682 doi "https://doi.org/10.1007/s11263-014-0798-1" @default.
- W1995766682 hasPublicationYear "2015" @default.
- W1995766682 type Work @default.
- W1995766682 sameAs 1995766682 @default.
- W1995766682 citedByCount "38" @default.
- W1995766682 countsByYear W19957666822014 @default.
- W1995766682 countsByYear W19957666822016 @default.
- W1995766682 countsByYear W19957666822017 @default.
- W1995766682 countsByYear W19957666822018 @default.
- W1995766682 countsByYear W19957666822019 @default.
- W1995766682 countsByYear W19957666822020 @default.
- W1995766682 countsByYear W19957666822021 @default.
- W1995766682 countsByYear W19957666822022 @default.
- W1995766682 crossrefType "journal-article" @default.
- W1995766682 hasAuthorship W1995766682A5012765543 @default.
- W1995766682 hasAuthorship W1995766682A5072882318 @default.
- W1995766682 hasBestOaLocation W19957666822 @default.
- W1995766682 hasConcept C119857082 @default.
- W1995766682 hasConcept C138885662 @default.
- W1995766682 hasConcept C154945302 @default.
- W1995766682 hasConcept C15744967 @default.
- W1995766682 hasConcept C170133592 @default.
- W1995766682 hasConcept C184337299 @default.
- W1995766682 hasConcept C199360897 @default.
- W1995766682 hasConcept C204321447 @default.
- W1995766682 hasConcept C23123220 @default.
- W1995766682 hasConcept C2777601683 @default.
- W1995766682 hasConcept C2780876879 @default.
- W1995766682 hasConcept C41008148 @default.
- W1995766682 hasConcept C41895202 @default.
- W1995766682 hasConcept C542102704 @default.
- W1995766682 hasConcept C90805587 @default.
- W1995766682 hasConcept C97931131 @default.
- W1995766682 hasConceptScore W1995766682C119857082 @default.
- W1995766682 hasConceptScore W1995766682C138885662 @default.
- W1995766682 hasConceptScore W1995766682C154945302 @default.
- W1995766682 hasConceptScore W1995766682C15744967 @default.
- W1995766682 hasConceptScore W1995766682C170133592 @default.
- W1995766682 hasConceptScore W1995766682C184337299 @default.
- W1995766682 hasConceptScore W1995766682C199360897 @default.
- W1995766682 hasConceptScore W1995766682C204321447 @default.
- W1995766682 hasConceptScore W1995766682C23123220 @default.
- W1995766682 hasConceptScore W1995766682C2777601683 @default.
- W1995766682 hasConceptScore W1995766682C2780876879 @default.
- W1995766682 hasConceptScore W1995766682C41008148 @default.
- W1995766682 hasConceptScore W1995766682C41895202 @default.
- W1995766682 hasConceptScore W1995766682C542102704 @default.
- W1995766682 hasConceptScore W1995766682C90805587 @default.
- W1995766682 hasConceptScore W1995766682C97931131 @default.
- W1995766682 hasIssue "1" @default.