Matches in SemOpenAlex for { <https://semopenalex.org/work/W2764318210> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W2764318210 abstract "Due to the progress of deep neural networks (DNN), DNN has been employed to cross-media retrieval. Existing cross-media retrieval methods based on DNN can convert separate representation of each media type to common representation by inter-media and intra-media constraints. By using common representation, we can measure similarities between heterogeneous instances and perform cross-media retrieval. However, it is challenging to optimize common representation learning due to the inter-media and intra-media constraints, which is a multi-objective optimization problem. This paper proposes residual correlation network (RCN) to address this issue. RCN optimizes common representation learning with a residual function, which can fit the optimal mapping from separate representation to common representation and relieve the multi-objective optimization problem. The experiments show that proposed approach achieves the best accuracy compared with 10 state-of-the-art methods on 3 datasets." @default.
- W2764318210 created "2017-10-20" @default.
- W2764318210 creator A5041307939 @default.
- W2764318210 creator A5047811387 @default.
- W2764318210 creator A5070178977 @default.
- W2764318210 date "2017-10-05" @default.
- W2764318210 modified "2023-10-16" @default.
- W2764318210 title "Cross-media residual correlation learning" @default.
- W2764318210 cites W1964073652 @default.
- W2764318210 cites W1997188340 @default.
- W2764318210 cites W2007972815 @default.
- W2764318210 cites W2013535308 @default.
- W2764318210 cites W2022398331 @default.
- W2764318210 cites W2053667957 @default.
- W2764318210 cites W2100235303 @default.
- W2764318210 cites W2106277773 @default.
- W2764318210 cites W2108598243 @default.
- W2764318210 cites W2155893237 @default.
- W2764318210 cites W2194775991 @default.
- W2764318210 cites W2606965845 @default.
- W2764318210 cites W4237723258 @default.
- W2764318210 doi "https://doi.org/10.1186/s40535-017-0038-1" @default.
- W2764318210 hasPublicationYear "2017" @default.
- W2764318210 type Work @default.
- W2764318210 sameAs 2764318210 @default.
- W2764318210 citedByCount "1" @default.
- W2764318210 countsByYear W27643182102018 @default.
- W2764318210 crossrefType "journal-article" @default.
- W2764318210 hasAuthorship W2764318210A5041307939 @default.
- W2764318210 hasAuthorship W2764318210A5047811387 @default.
- W2764318210 hasAuthorship W2764318210A5070178977 @default.
- W2764318210 hasBestOaLocation W27643182101 @default.
- W2764318210 hasConcept C11413529 @default.
- W2764318210 hasConcept C117220453 @default.
- W2764318210 hasConcept C119857082 @default.
- W2764318210 hasConcept C154945302 @default.
- W2764318210 hasConcept C155512373 @default.
- W2764318210 hasConcept C17744445 @default.
- W2764318210 hasConcept C199539241 @default.
- W2764318210 hasConcept C2524010 @default.
- W2764318210 hasConcept C2776359362 @default.
- W2764318210 hasConcept C33923547 @default.
- W2764318210 hasConcept C41008148 @default.
- W2764318210 hasConcept C50644808 @default.
- W2764318210 hasConcept C59404180 @default.
- W2764318210 hasConcept C94625758 @default.
- W2764318210 hasConceptScore W2764318210C11413529 @default.
- W2764318210 hasConceptScore W2764318210C117220453 @default.
- W2764318210 hasConceptScore W2764318210C119857082 @default.
- W2764318210 hasConceptScore W2764318210C154945302 @default.
- W2764318210 hasConceptScore W2764318210C155512373 @default.
- W2764318210 hasConceptScore W2764318210C17744445 @default.
- W2764318210 hasConceptScore W2764318210C199539241 @default.
- W2764318210 hasConceptScore W2764318210C2524010 @default.
- W2764318210 hasConceptScore W2764318210C2776359362 @default.
- W2764318210 hasConceptScore W2764318210C33923547 @default.
- W2764318210 hasConceptScore W2764318210C41008148 @default.
- W2764318210 hasConceptScore W2764318210C50644808 @default.
- W2764318210 hasConceptScore W2764318210C59404180 @default.
- W2764318210 hasConceptScore W2764318210C94625758 @default.
- W2764318210 hasFunder F4320321001 @default.
- W2764318210 hasLocation W27643182101 @default.
- W2764318210 hasOpenAccess W2764318210 @default.
- W2764318210 hasPrimaryLocation W27643182101 @default.
- W2764318210 hasRelatedWork W136628379 @default.
- W2764318210 hasRelatedWork W1520228060 @default.
- W2764318210 hasRelatedWork W1572378471 @default.
- W2764318210 hasRelatedWork W2037715382 @default.
- W2764318210 hasRelatedWork W2049579705 @default.
- W2764318210 hasRelatedWork W2078116075 @default.
- W2764318210 hasRelatedWork W2461411508 @default.
- W2764318210 hasRelatedWork W2476034201 @default.
- W2764318210 hasRelatedWork W2533412408 @default.
- W2764318210 hasRelatedWork W2560619722 @default.
- W2764318210 hasRelatedWork W2740797857 @default.
- W2764318210 hasRelatedWork W2893076700 @default.
- W2764318210 hasRelatedWork W2906705760 @default.
- W2764318210 hasRelatedWork W2963022926 @default.
- W2764318210 hasRelatedWork W2969657373 @default.
- W2764318210 hasRelatedWork W2982476267 @default.
- W2764318210 hasRelatedWork W3081475880 @default.
- W2764318210 hasRelatedWork W3094658021 @default.
- W2764318210 hasRelatedWork W3107593279 @default.
- W2764318210 hasRelatedWork W3163957165 @default.
- W2764318210 isParatext "false" @default.
- W2764318210 isRetracted "false" @default.
- W2764318210 magId "2764318210" @default.
- W2764318210 workType "article" @default.