FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2316082076> ?p ?o ?g. }

• W2316082076 endingPage "1216" @default.
• W2316082076 startingPage "1201" @default.
• W2316082076 abstract "With the explosive growth of web data, effective and efficient technologies are in urgent need for retrieving semantically relevant contents of heterogeneous modalities. Previous studies devote efforts to modeling simple cross-modal statistical dependencies, and globally projecting the heterogeneous modalities into a measurable subspace. However, global projections cannot appropriately adapt to diverse contents, and the naturally existing multilevel semantic relation in web data is ignored. We study the problem of semantic coherent retrieval, where documents from different modalities should be ranked by the semantic relevance to the query. Accordingly, we propose TINA, a correlation learning method by adaptive hierarchical semantic aggregation. First, by joint modeling of content and ontology similarities, we build a semantic hierarchy to measure multilevel semantic relevance. Second, with a set of local linear projections and probabilistic membership functions, we propose two paradigms for local expert aggregation, i.e., local projection aggregation and local distance aggregation. To learn the cross-modal projections, we optimize the structure risk objective function that involves semantic coherence measurement, local projection consistency, and the complexity penalty of local projections. Compared to existing approaches, a better bias-variance tradeoff is achieved by TINA in real-world cross-modal correlation learning tasks. Extensive experiments on widely used NUS-WIDE and ICML-Challenge for image–text retrieval demonstrate that TINA better adapts to the multilevel semantic relation and content divergence, and, thus, outperforms state of the art with better semantic coherence." @default.
• W2316082076 created "2016-06-24" @default.
• W2316082076 creator A5008183522 @default.
• W2316082076 creator A5027394471 @default.
• W2316082076 creator A5028597017 @default.
• W2316082076 creator A5034112897 @default.
• W2316082076 creator A5055640195 @default.
• W2316082076 date "2016-06-01" @default.
• W2316082076 modified "2023-09-27" @default.
• W2316082076 title "Cross-Modal Correlation Learning by Adaptive Hierarchical Semantic Aggregation" @default.
• W2316082076 cites W1965963232 @default.
• W2316082076 cites W1970055505 @default.
• W2316082076 cites W1978962787 @default.
• W2316082076 cites W1979936637 @default.
• W2316082076 cites W1996219872 @default.
• W2316082076 cites W2007972815 @default.
• W2316082076 cites W2014655365 @default.
• W2316082076 cites W2015175493 @default.
• W2316082076 cites W2019863495 @default.
• W2316082076 cites W2025341678 @default.
• W2316082076 cites W2033823371 @default.
• W2316082076 cites W2038436420 @default.
• W2316082076 cites W2047632871 @default.
• W2316082076 cites W2049993534 @default.
• W2316082076 cites W2061851712 @default.
• W2316082076 cites W2064797228 @default.
• W2316082076 cites W2070753207 @default.
• W2316082076 cites W2071207147 @default.
• W2316082076 cites W2076455317 @default.
• W2316082076 cites W2077692330 @default.
• W2316082076 cites W2083095455 @default.
• W2316082076 cites W2087193308 @default.
• W2316082076 cites W2093192785 @default.
• W2316082076 cites W2106277773 @default.
• W2316082076 cites W2112193096 @default.
• W2316082076 cites W2116339064 @default.
• W2316082076 cites W2134665698 @default.
• W2316082076 cites W2136480620 @default.
• W2316082076 cites W2136930489 @default.
• W2316082076 cites W2137225583 @default.
• W2316082076 cites W2139882085 @default.
• W2316082076 cites W2155893237 @default.
• W2316082076 cites W2165673880 @default.
• W2316082076 cites W2168371480 @default.
• W2316082076 cites W4235505822 @default.
• W2316082076 cites W4251308012 @default.
• W2316082076 doi "https://doi.org/10.1109/tmm.2016.2535864" @default.
• W2316082076 hasPublicationYear "2016" @default.
• W2316082076 type Work @default.
• W2316082076 sameAs 2316082076 @default.
• W2316082076 citedByCount "45" @default.
• W2316082076 countsByYear W23160820762016 @default.
• W2316082076 countsByYear W23160820762017 @default.
• W2316082076 countsByYear W23160820762018 @default.
• W2316082076 countsByYear W23160820762019 @default.
• W2316082076 countsByYear W23160820762020 @default.
• W2316082076 countsByYear W23160820762021 @default.
• W2316082076 countsByYear W23160820762022 @default.
• W2316082076 countsByYear W23160820762023 @default.
• W2316082076 crossrefType "journal-article" @default.
• W2316082076 hasAuthorship W2316082076A5008183522 @default.
• W2316082076 hasAuthorship W2316082076A5027394471 @default.
• W2316082076 hasAuthorship W2316082076A5028597017 @default.
• W2316082076 hasAuthorship W2316082076A5034112897 @default.
• W2316082076 hasAuthorship W2316082076A5055640195 @default.
• W2316082076 hasConcept C117220453 @default.
• W2316082076 hasConcept C119857082 @default.
• W2316082076 hasConcept C154945302 @default.
• W2316082076 hasConcept C185592680 @default.
• W2316082076 hasConcept C188027245 @default.
• W2316082076 hasConcept C204321447 @default.
• W2316082076 hasConcept C2524010 @default.
• W2316082076 hasConcept C33923547 @default.
• W2316082076 hasConcept C41008148 @default.
• W2316082076 hasConcept C71139939 @default.
• W2316082076 hasConceptScore W2316082076C117220453 @default.
• W2316082076 hasConceptScore W2316082076C119857082 @default.
• W2316082076 hasConceptScore W2316082076C154945302 @default.
• W2316082076 hasConceptScore W2316082076C185592680 @default.
• W2316082076 hasConceptScore W2316082076C188027245 @default.
• W2316082076 hasConceptScore W2316082076C204321447 @default.
• W2316082076 hasConceptScore W2316082076C2524010 @default.
• W2316082076 hasConceptScore W2316082076C33923547 @default.
• W2316082076 hasConceptScore W2316082076C41008148 @default.
• W2316082076 hasConceptScore W2316082076C71139939 @default.
• W2316082076 hasIssue "6" @default.
• W2316082076 hasLocation W23160820761 @default.
• W2316082076 hasOpenAccess W2316082076 @default.
• W2316082076 hasPrimaryLocation W23160820761 @default.
• W2316082076 hasRelatedWork W2368651715 @default.
• W2316082076 hasRelatedWork W2611614995 @default.
• W2316082076 hasRelatedWork W2961085424 @default.
• W2316082076 hasRelatedWork W3046775127 @default.
• W2316082076 hasRelatedWork W3107474891 @default.
• W2316082076 hasRelatedWork W4205958290 @default.
• W2316082076 hasRelatedWork W4286629047 @default.
• W2316082076 hasRelatedWork W4306321456 @default.
• W2316082076 hasRelatedWork W4306674287 @default.

• next