FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894879246> ?p ?o ?g. }

• W2894879246 endingPage "1440" @default.
• W2894879246 startingPage "1429" @default.
• W2894879246 abstract "Cross-modal hashing has attracted increasing research attention due to its efficiency for large-scale multimedia retrieval. With simultaneous feature representation and hash function learning, deep cross-modal hashing (DCMH) methods have shown superior performance. However, most existing methods on DCMH adopt binary quantization functions (e.g., [Formula: see text]) to generate hash codes, which limit the retrieval performance since binary quantization functions are sensitive to the variations of numeric values. Toward this end, we propose a novel end-to-end ranking-based hashing framework, in this paper, termed as deep semantic-preserving ordinal hashing (DSPOH), to learn hash functions with deep neural networks by exploring the ranking structure of feature dimensions. In DSPOH, the ordinal representation, which encodes the relative rank ordering of feature dimensions, is explored to generate hash codes. Such ordinal embedding benefits from the numeric stability of rank correlation measures. To make the hash codes discriminative, the ordinal representation is expected to well predict the class labels so that the ranking-based hash function learning is optimally compatible with the label predicting. Meanwhile, the intermodality similarity is preserved to guarantee that the hash codes of different modalities are consistent. Importantly, DSPOH can be effectively integrated with different types of network architectures, which demonstrates the flexibility and scalability of our proposed hashing framework. Extensive experiments on three widely used multimodal data sets show that DSPOH outperforms state of the art for cross-modal retrieval tasks." @default.
• W2894879246 created "2018-10-12" @default.
• W2894879246 creator A5001671734 @default.
• W2894879246 creator A5017096005 @default.
• W2894879246 creator A5035112538 @default.
• W2894879246 creator A5076586054 @default.
• W2894879246 creator A5076666788 @default.
• W2894879246 creator A5082230753 @default.
• W2894879246 date "2019-05-01" @default.
• W2894879246 modified "2023-10-14" @default.
• W2894879246 title "Deep Semantic-Preserving Ordinal Hashing for Cross-Modal Similarity Search" @default.
• W2894879246 cites W1566135517 @default.
• W2894879246 cites W1777628566 @default.
• W2894879246 cites W1885185971 @default.
• W2894879246 cites W1903029394 @default.
• W2894879246 cites W1922199343 @default.
• W2894879246 cites W1950117310 @default.
• W2894879246 cites W1964073652 @default.
• W2894879246 cites W1970055505 @default.
• W2894879246 cites W1976258951 @default.
• W2894879246 cites W1983364832 @default.
• W2894879246 cites W1997107867 @default.
• W2894879246 cites W2007972815 @default.
• W2894879246 cites W2015175493 @default.
• W2894879246 cites W2022398331 @default.
• W2894879246 cites W2049993534 @default.
• W2894879246 cites W2057228822 @default.
• W2894879246 cites W2064797228 @default.
• W2894879246 cites W2081193615 @default.
• W2894879246 cites W2086958058 @default.
• W2894879246 cites W2087193308 @default.
• W2894879246 cites W2106277773 @default.
• W2894879246 cites W2110990863 @default.
• W2894879246 cites W2140619591 @default.
• W2894879246 cites W2151103935 @default.
• W2894879246 cites W2155893237 @default.
• W2894879246 cites W2159373756 @default.
• W2894879246 cites W2161381512 @default.
• W2894879246 cites W2194187530 @default.
• W2894879246 cites W2194775991 @default.
• W2894879246 cites W2240067561 @default.
• W2894879246 cites W2251084241 @default.
• W2894879246 cites W2266728343 @default.
• W2894879246 cites W2295038166 @default.
• W2894879246 cites W2388114291 @default.
• W2894879246 cites W2411707397 @default.
• W2894879246 cites W2418353079 @default.
• W2894879246 cites W2425857666 @default.
• W2894879246 cites W2441255125 @default.
• W2894879246 cites W2461972671 @default.
• W2894879246 cites W2547411571 @default.
• W2894879246 cites W2559348937 @default.
• W2894879246 cites W2586937979 @default.
• W2894879246 cites W2594227027 @default.
• W2894879246 cites W2624945720 @default.
• W2894879246 cites W2801765193 @default.
• W2894879246 cites W2919115771 @default.
• W2894879246 cites W4251308012 @default.
• W2894879246 doi "https://doi.org/10.1109/tnnls.2018.2869601" @default.
• W2894879246 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/30281496" @default.
• W2894879246 hasPublicationYear "2019" @default.
• W2894879246 type Work @default.
• W2894879246 sameAs 2894879246 @default.
• W2894879246 citedByCount "51" @default.
• W2894879246 countsByYear W28948792462018 @default.
• W2894879246 countsByYear W28948792462019 @default.
• W2894879246 countsByYear W28948792462020 @default.
• W2894879246 countsByYear W28948792462021 @default.
• W2894879246 countsByYear W28948792462022 @default.
• W2894879246 countsByYear W28948792462023 @default.
• W2894879246 crossrefType "journal-article" @default.
• W2894879246 hasAuthorship W2894879246A5001671734 @default.
• W2894879246 hasAuthorship W2894879246A5017096005 @default.
• W2894879246 hasAuthorship W2894879246A5035112538 @default.
• W2894879246 hasAuthorship W2894879246A5076586054 @default.
• W2894879246 hasAuthorship W2894879246A5076666788 @default.
• W2894879246 hasAuthorship W2894879246A5082230753 @default.
• W2894879246 hasConcept C116058348 @default.
• W2894879246 hasConcept C122907437 @default.
• W2894879246 hasConcept C124101348 @default.
• W2894879246 hasConcept C133667856 @default.
• W2894879246 hasConcept C138111711 @default.
• W2894879246 hasConcept C153180895 @default.
• W2894879246 hasConcept C154945302 @default.
• W2894879246 hasConcept C33923547 @default.
• W2894879246 hasConcept C38652104 @default.
• W2894879246 hasConcept C41008148 @default.
• W2894879246 hasConcept C48372109 @default.
• W2894879246 hasConcept C63435697 @default.
• W2894879246 hasConcept C67388219 @default.
• W2894879246 hasConcept C80444323 @default.
• W2894879246 hasConcept C94375191 @default.
• W2894879246 hasConcept C99138194 @default.
• W2894879246 hasConceptScore W2894879246C116058348 @default.
• W2894879246 hasConceptScore W2894879246C122907437 @default.
• W2894879246 hasConceptScore W2894879246C124101348 @default.
• W2894879246 hasConceptScore W2894879246C133667856 @default.
• W2894879246 hasConceptScore W2894879246C138111711 @default.

• next