FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996002873> ?p ?o ?g. }

• W2996002873 endingPage "96" @default.
• W2996002873 startingPage "84" @default.
• W2996002873 abstract "Unsupervised cross-modal hashing learns hash codes without dependence on the semantic labels. It has the desirable advantage of well scalability and thus can effectively support large-scale cross-media retrieval. However, how to directly learn discriminative discrete hash codes under the unsupervised learning paradigm is still an open challenging problem. In this paper, we aim to attack this problem by proposing an Unsupervised Deep Cross-modal Hashing with Virtual Label Regression (UDCH-VLR) method. We propose a novel unified learning framework to jointly perform deep hash function training, virtual label learning and regression. Specifically, we learn unified hash codes via collaborative matrix factorization on the multi-modal deep representations to preserve the multi-modal shared semantics. Further, we incorporate the virtual label learning into the objective functions and simultaneously regress the learned virtual labels to the hash codes. Finally, instead of simply exploiting the existing shallow features and relaxing the binary constraints, we devise an alternative optimization strategy to directly update the deep hash functions and discrete binary codes. Under such circumstance, the discriminative capability of hash codes can be progressively enhanced with iterative learning. Extensive experiments on three publicly available cross-media retrieval datasets demonstrate that our approach outperforms state-of-the-art methods." @default.
• W2996002873 created "2019-12-26" @default.
• W2996002873 creator A5008391423 @default.
• W2996002873 creator A5049521186 @default.
• W2996002873 creator A5051630734 @default.
• W2996002873 creator A5068843001 @default.
• W2996002873 creator A5083455588 @default.
• W2996002873 date "2020-04-01" @default.
• W2996002873 modified "2023-10-15" @default.
• W2996002873 title "Unsupervised Deep Cross-modal Hashing with Virtual Label Regression" @default.
• W2996002873 cites W1566135517 @default.
• W2996002873 cites W2001359285 @default.
• W2996002873 cites W2162316550 @default.
• W2996002873 cites W2211092169 @default.
• W2996002873 cites W2322020277 @default.
• W2996002873 cites W2345649690 @default.
• W2996002873 cites W2345812103 @default.
• W2996002873 cites W2534014507 @default.
• W2996002873 cites W2560982456 @default.
• W2996002873 cites W2589266112 @default.
• W2996002873 cites W2591669147 @default.
• W2996002873 cites W2733636222 @default.
• W2996002873 cites W2781821509 @default.
• W2996002873 cites W2791731057 @default.
• W2996002873 cites W2793456900 @default.
• W2996002873 cites W2801477643 @default.
• W2996002873 cites W2803696107 @default.
• W2996002873 cites W2805087257 @default.
• W2996002873 cites W2887712318 @default.
• W2996002873 cites W2889024947 @default.
• W2996002873 cites W2889418103 @default.
• W2996002873 cites W2892946488 @default.
• W2996002873 cites W2896399498 @default.
• W2996002873 cites W2900806287 @default.
• W2996002873 cites W2907166662 @default.
• W2996002873 cites W2922420408 @default.
• W2996002873 cites W2963634791 @default.
• W2996002873 cites W2971949219 @default.
• W2996002873 doi "https://doi.org/10.1016/j.neucom.2019.12.058" @default.
• W2996002873 hasPublicationYear "2020" @default.
• W2996002873 type Work @default.
• W2996002873 sameAs 2996002873 @default.
• W2996002873 citedByCount "31" @default.
• W2996002873 countsByYear W29960028732020 @default.
• W2996002873 countsByYear W29960028732021 @default.
• W2996002873 countsByYear W29960028732022 @default.
• W2996002873 countsByYear W29960028732023 @default.
• W2996002873 crossrefType "journal-article" @default.
• W2996002873 hasAuthorship W2996002873A5008391423 @default.
• W2996002873 hasAuthorship W2996002873A5049521186 @default.
• W2996002873 hasAuthorship W2996002873A5051630734 @default.
• W2996002873 hasAuthorship W2996002873A5068843001 @default.
• W2996002873 hasAuthorship W2996002873A5083455588 @default.
• W2996002873 hasConcept C109718341 @default.
• W2996002873 hasConcept C116058348 @default.
• W2996002873 hasConcept C119857082 @default.
• W2996002873 hasConcept C122907437 @default.
• W2996002873 hasConcept C124101348 @default.
• W2996002873 hasConcept C133667856 @default.
• W2996002873 hasConcept C138111711 @default.
• W2996002873 hasConcept C145671259 @default.
• W2996002873 hasConcept C153180895 @default.
• W2996002873 hasConcept C154945302 @default.
• W2996002873 hasConcept C33923547 @default.
• W2996002873 hasConcept C38652104 @default.
• W2996002873 hasConcept C41008148 @default.
• W2996002873 hasConcept C48044578 @default.
• W2996002873 hasConcept C48372109 @default.
• W2996002873 hasConcept C63435697 @default.
• W2996002873 hasConcept C67388219 @default.
• W2996002873 hasConcept C77088390 @default.
• W2996002873 hasConcept C80444323 @default.
• W2996002873 hasConcept C94375191 @default.
• W2996002873 hasConcept C97931131 @default.
• W2996002873 hasConcept C99138194 @default.
• W2996002873 hasConceptScore W2996002873C109718341 @default.
• W2996002873 hasConceptScore W2996002873C116058348 @default.
• W2996002873 hasConceptScore W2996002873C119857082 @default.
• W2996002873 hasConceptScore W2996002873C122907437 @default.
• W2996002873 hasConceptScore W2996002873C124101348 @default.
• W2996002873 hasConceptScore W2996002873C133667856 @default.
• W2996002873 hasConceptScore W2996002873C138111711 @default.
• W2996002873 hasConceptScore W2996002873C145671259 @default.
• W2996002873 hasConceptScore W2996002873C153180895 @default.
• W2996002873 hasConceptScore W2996002873C154945302 @default.
• W2996002873 hasConceptScore W2996002873C33923547 @default.
• W2996002873 hasConceptScore W2996002873C38652104 @default.
• W2996002873 hasConceptScore W2996002873C41008148 @default.
• W2996002873 hasConceptScore W2996002873C48044578 @default.
• W2996002873 hasConceptScore W2996002873C48372109 @default.
• W2996002873 hasConceptScore W2996002873C63435697 @default.
• W2996002873 hasConceptScore W2996002873C67388219 @default.
• W2996002873 hasConceptScore W2996002873C77088390 @default.
• W2996002873 hasConceptScore W2996002873C80444323 @default.
• W2996002873 hasConceptScore W2996002873C94375191 @default.
• W2996002873 hasConceptScore W2996002873C97931131 @default.
• W2996002873 hasConceptScore W2996002873C99138194 @default.
• W2996002873 hasFunder F4320321001 @default.

• next