FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3182020042> ?p ?o ?g. }

• W3182020042 endingPage "108153" @default.
• W3182020042 startingPage "108153" @default.
• W3182020042 abstract "• A knowledge base graph embedding module is constructed to extend the generality of the visual question answering model based on knowledge base in this paper. • This paper constructs two experimental knowledge bases: DBV and DBA through a series of knowledge base preprocessing methods. • The DBV knowledge base constructed in this paper has strong entity correspondence, and its knowledge base embedding effect is very good. In this paper, a knowledge base graph embedding module is constructed to extend the versatility of knowledge-based VQA (Visual Question Answering) models. The knowledge base graph embedding module constructed in this paper extracts core entities from images and text, and maps them as knowledge base entities, then extracts the sub-graphs closely related to the core entities, and converts the sub-graphs into low-dimensional vectors to realize sub-graph embedding. In order to achieve good subgraph embedding, we first extracted two experimental knowledge bases with rich semantics from DBpedia: DBV and DBA. Based on these two knowledge bases, this paper selects several excellent models in knowledge base embedding as test models, including SE (structured embedding),SME(semantic matching energy function), and TransE model to produce link prediction. The results show that there is a clear correspondence between the entities of the DBV, which can achieve excellent node embedding. And the TransE model can achieve a good knowledge base embedding, so we built the knowledge base graph embedding module based on TransE. And then we construct a VQA model ( KBSN ) based on the knowledge base graph embedding. Experimental results on VQA2.0 and KB-VQA data sets prove that the knowledge base graph embedding module improves the accuracy." @default.
• W3182020042 created "2021-07-19" @default.
• W3182020042 creator A5014822993 @default.
• W3182020042 creator A5023971713 @default.
• W3182020042 creator A5055305719 @default.
• W3182020042 creator A5062384828 @default.
• W3182020042 creator A5075944989 @default.
• W3182020042 creator A5082496274 @default.
• W3182020042 date "2021-12-01" @default.
• W3182020042 modified "2023-10-17" @default.
• W3182020042 title "Knowledge base graph embedding module design for Visual question answering model" @default.
• W3182020042 cites W1990060916 @default.
• W3182020042 cites W2037751681 @default.
• W3182020042 cites W2080133951 @default.
• W3182020042 cites W2218543863 @default.
• W3182020042 cites W2255436302 @default.
• W3182020042 cites W2564242866 @default.
• W3182020042 cites W2570877474 @default.
• W3182020042 cites W2741437009 @default.
• W3182020042 cites W2748460711 @default.
• W3182020042 cites W2907571587 @default.
• W3182020042 cites W2913943056 @default.
• W3182020042 cites W2964303913 @default.
• W3182020042 cites W2968843694 @default.
• W3182020042 cites W2971359695 @default.
• W3182020042 cites W3001080452 @default.
• W3182020042 cites W3002683472 @default.
• W3182020042 cites W3033517123 @default.
• W3182020042 cites W3041222599 @default.
• W3182020042 cites W3044175177 @default.
• W3182020042 cites W3109584340 @default.
• W3182020042 cites W3128596500 @default.
• W3182020042 cites W3134284227 @default.
• W3182020042 cites W639708223 @default.
• W3182020042 cites W68132019 @default.
• W3182020042 doi "https://doi.org/10.1016/j.patcog.2021.108153" @default.
• W3182020042 hasPublicationYear "2021" @default.
• W3182020042 type Work @default.
• W3182020042 sameAs 3182020042 @default.
• W3182020042 citedByCount "140" @default.
• W3182020042 countsByYear W31820200422021 @default.
• W3182020042 countsByYear W31820200422022 @default.
• W3182020042 countsByYear W31820200422023 @default.
• W3182020042 crossrefType "journal-article" @default.
• W3182020042 hasAuthorship W3182020042A5014822993 @default.
• W3182020042 hasAuthorship W3182020042A5023971713 @default.
• W3182020042 hasAuthorship W3182020042A5055305719 @default.
• W3182020042 hasAuthorship W3182020042A5062384828 @default.
• W3182020042 hasAuthorship W3182020042A5075944989 @default.
• W3182020042 hasAuthorship W3182020042A5082496274 @default.
• W3182020042 hasConcept C132525143 @default.
• W3182020042 hasConcept C134306372 @default.
• W3182020042 hasConcept C154945302 @default.
• W3182020042 hasConcept C2987255567 @default.
• W3182020042 hasConcept C33923547 @default.
• W3182020042 hasConcept C41008148 @default.
• W3182020042 hasConcept C41608201 @default.
• W3182020042 hasConcept C42058472 @default.
• W3182020042 hasConcept C44291984 @default.
• W3182020042 hasConcept C4554734 @default.
• W3182020042 hasConcept C80444323 @default.
• W3182020042 hasConceptScore W3182020042C132525143 @default.
• W3182020042 hasConceptScore W3182020042C134306372 @default.
• W3182020042 hasConceptScore W3182020042C154945302 @default.
• W3182020042 hasConceptScore W3182020042C2987255567 @default.
• W3182020042 hasConceptScore W3182020042C33923547 @default.
• W3182020042 hasConceptScore W3182020042C41008148 @default.
• W3182020042 hasConceptScore W3182020042C41608201 @default.
• W3182020042 hasConceptScore W3182020042C42058472 @default.
• W3182020042 hasConceptScore W3182020042C44291984 @default.
• W3182020042 hasConceptScore W3182020042C4554734 @default.
• W3182020042 hasConceptScore W3182020042C80444323 @default.
• W3182020042 hasFunder F4320333335 @default.
• W3182020042 hasLocation W31820200421 @default.
• W3182020042 hasOpenAccess W3182020042 @default.
• W3182020042 hasPrimaryLocation W31820200421 @default.
• W3182020042 hasRelatedWork W2551237228 @default.
• W3182020042 hasRelatedWork W2579831760 @default.
• W3182020042 hasRelatedWork W2784239688 @default.
• W3182020042 hasRelatedWork W2791913352 @default.
• W3182020042 hasRelatedWork W2896255488 @default.
• W3182020042 hasRelatedWork W2923818335 @default.
• W3182020042 hasRelatedWork W2963380480 @default.
• W3182020042 hasRelatedWork W3182020042 @default.
• W3182020042 hasRelatedWork W4226361842 @default.
• W3182020042 hasRelatedWork W4312937211 @default.
• W3182020042 hasVolume "120" @default.
• W3182020042 isParatext "false" @default.
• W3182020042 isRetracted "false" @default.
• W3182020042 magId "3182020042" @default.
• W3182020042 workType "article" @default.