Matches in SemOpenAlex for { <https://semopenalex.org/work/W1978689620> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W1978689620 abstract "With the explosive growth of web data, effective and efficient technologies are in urgent needs for retrieving semantically relevant contents of heterogeneous modalities. Previous studies construct global transformations to project the heterogeneous data into a measurable subspace. However, global projections cannot appropriately adapt to diverse contents, and the naturally existing multi-level 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 queries. 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 multi-level semantic relevance. Second, with a set of local linear projections aggregated by gating functions, we optimize the structure risk objective function that involves semantic coherence measurement, local projection consistency and the complexity penalty of local projections. Therefore, semantic coherence and a better bias-variance trade-off can be achieved by TINA. Extensive experiments on widely used NUS-WIDE and ICML-Challenge datasets demonstrate that TINA outperforms state-of-the-art, and achieves better adaptation to the multi-level semantic relation and content divergence." @default.
- W1978689620 created "2016-06-24" @default.
- W1978689620 creator A5008183522 @default.
- W1978689620 creator A5027394471 @default.
- W1978689620 creator A5028597017 @default.
- W1978689620 creator A5034112897 @default.
- W1978689620 creator A5055640195 @default.
- W1978689620 date "2014-12-01" @default.
- W1978689620 modified "2023-09-27" @default.
- W1978689620 title "TINA: Cross-Modal Correlation Learning by Adaptive Hierarchical Semantic Aggregation" @default.
- W1978689620 cites W1970055505 @default.
- W1978689620 cites W1978962787 @default.
- W1978689620 cites W1979936637 @default.
- W1978689620 cites W2004011892 @default.
- W1978689620 cites W2007972815 @default.
- W1978689620 cites W2025341678 @default.
- W1978689620 cites W2047632871 @default.
- W1978689620 cites W2049993534 @default.
- W1978689620 cites W2061851712 @default.
- W1978689620 cites W2064797228 @default.
- W1978689620 cites W2076455317 @default.
- W1978689620 cites W2106277773 @default.
- W1978689620 cites W2116339064 @default.
- W1978689620 cites W2134665698 @default.
- W1978689620 cites W2136480620 @default.
- W1978689620 cites W2136930489 @default.
- W1978689620 cites W2150884987 @default.
- W1978689620 cites W2168371480 @default.
- W1978689620 cites W2885517846 @default.
- W1978689620 cites W4235505822 @default.
- W1978689620 cites W4248892431 @default.
- W1978689620 doi "https://doi.org/10.1109/icdm.2014.65" @default.
- W1978689620 hasPublicationYear "2014" @default.
- W1978689620 type Work @default.
- W1978689620 sameAs 1978689620 @default.
- W1978689620 citedByCount "7" @default.
- W1978689620 countsByYear W19786896202015 @default.
- W1978689620 countsByYear W19786896202017 @default.
- W1978689620 countsByYear W19786896202019 @default.
- W1978689620 crossrefType "proceedings-article" @default.
- W1978689620 hasAuthorship W1978689620A5008183522 @default.
- W1978689620 hasAuthorship W1978689620A5027394471 @default.
- W1978689620 hasAuthorship W1978689620A5028597017 @default.
- W1978689620 hasAuthorship W1978689620A5034112897 @default.
- W1978689620 hasAuthorship W1978689620A5055640195 @default.
- W1978689620 hasConcept C154945302 @default.
- W1978689620 hasConcept C2129575 @default.
- W1978689620 hasConcept C23123220 @default.
- W1978689620 hasConcept C37926939 @default.
- W1978689620 hasConcept C41008148 @default.
- W1978689620 hasConcept C511149849 @default.
- W1978689620 hasConcept C534406577 @default.
- W1978689620 hasConceptScore W1978689620C154945302 @default.
- W1978689620 hasConceptScore W1978689620C2129575 @default.
- W1978689620 hasConceptScore W1978689620C23123220 @default.
- W1978689620 hasConceptScore W1978689620C37926939 @default.
- W1978689620 hasConceptScore W1978689620C41008148 @default.
- W1978689620 hasConceptScore W1978689620C511149849 @default.
- W1978689620 hasConceptScore W1978689620C534406577 @default.
- W1978689620 hasLocation W19786896201 @default.
- W1978689620 hasOpenAccess W1978689620 @default.
- W1978689620 hasPrimaryLocation W19786896201 @default.
- W1978689620 hasRelatedWork W146038348 @default.
- W1978689620 hasRelatedWork W1801052627 @default.
- W1978689620 hasRelatedWork W2348459908 @default.
- W1978689620 hasRelatedWork W2351790455 @default.
- W1978689620 hasRelatedWork W2352490706 @default.
- W1978689620 hasRelatedWork W2355894329 @default.
- W1978689620 hasRelatedWork W2379099092 @default.
- W1978689620 hasRelatedWork W2380556669 @default.
- W1978689620 hasRelatedWork W2391768008 @default.
- W1978689620 hasRelatedWork W2800975405 @default.
- W1978689620 isParatext "false" @default.
- W1978689620 isRetracted "false" @default.
- W1978689620 magId "1978689620" @default.
- W1978689620 workType "article" @default.