Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386089418> ?p ?o ?g. }
- W4386089418 abstract "Abstract Currently, there are various widely used methods for hashing-based cross modal retrieval to achieve promising performance in the information retrieval task. However, the challenge of learning discriminative representations against a heterogeneous gap in the case of multi-modal data still needs to be explored. Most existing methods directly project raw heterogeneous data linearly onto a common projection space, leading to high projection error because the semantic similarity of multi-modal data is not captured. We need the efficient feature representation of heterogeneous and multi-modal data to learn high-quality discrete hash codes and improve retrieval performance. This paper proposes a label-consistent kernel transform learning-based sparse hashing (LcKTLSH) for cross modal retrieval. Instead of projecting raw data samples, LcKTLSH learns transform and sparse coefficients suited for projection onto the kernel space, assuming each modality of a single instance has a unique hash code. The learned sparse coefficients are embedded into pre-learned hash codes, and semantic information from the similarity matrix is embedded into pre-learned hash codes to generate final hash codes. Kernel trick accounts for non-linearity in the data, and label-consistency constraint acts as the supervision term. Extensive experimental results on four benchmark datasets significantly advance over previous investigations." @default.
- W4386089418 created "2023-08-24" @default.
- W4386089418 creator A5061490660 @default.
- W4386089418 date "2023-08-24" @default.
- W4386089418 modified "2023-10-01" @default.
- W4386089418 title "Label-consistent Kernel Transform Learning based Sparse Hashing for cross-modal retrieval" @default.
- W4386089418 cites W1922199343 @default.
- W4386089418 cites W1964255607 @default.
- W4386089418 cites W1989833002 @default.
- W4386089418 cites W2002932002 @default.
- W4386089418 cites W2006147162 @default.
- W4386089418 cites W2039771911 @default.
- W4386089418 cites W2100235303 @default.
- W4386089418 cites W2106277773 @default.
- W4386089418 cites W2145962650 @default.
- W4386089418 cites W2150886314 @default.
- W4386089418 cites W2155803963 @default.
- W4386089418 cites W2192994569 @default.
- W4386089418 cites W2199369932 @default.
- W4386089418 cites W2203543769 @default.
- W4386089418 cites W2266728343 @default.
- W4386089418 cites W2274047922 @default.
- W4386089418 cites W2545426943 @default.
- W4386089418 cites W2565716668 @default.
- W4386089418 cites W2591669147 @default.
- W4386089418 cites W2748725735 @default.
- W4386089418 cites W2753163043 @default.
- W4386089418 cites W2756249521 @default.
- W4386089418 cites W2890271586 @default.
- W4386089418 cites W2891193211 @default.
- W4386089418 cites W2896038883 @default.
- W4386089418 cites W2907166662 @default.
- W4386089418 cites W2922179541 @default.
- W4386089418 cites W2949588459 @default.
- W4386089418 cites W2962853966 @default.
- W4386089418 cites W2962955826 @default.
- W4386089418 cites W2963173190 @default.
- W4386089418 cites W2963288100 @default.
- W4386089418 cites W2978758977 @default.
- W4386089418 cites W2997143100 @default.
- W4386089418 cites W3008072721 @default.
- W4386089418 cites W3011671077 @default.
- W4386089418 cites W3028385587 @default.
- W4386089418 cites W3033799362 @default.
- W4386089418 cites W3046172533 @default.
- W4386089418 cites W3122091215 @default.
- W4386089418 cites W3136345137 @default.
- W4386089418 cites W3166240318 @default.
- W4386089418 cites W3175419680 @default.
- W4386089418 cites W4224217755 @default.
- W4386089418 cites W4282937884 @default.
- W4386089418 cites W4284977495 @default.
- W4386089418 cites W4285308876 @default.
- W4386089418 cites W4292363360 @default.
- W4386089418 cites W4309531267 @default.
- W4386089418 cites W4309835919 @default.
- W4386089418 cites W4378417719 @default.
- W4386089418 doi "https://doi.org/10.21203/rs.3.rs-3284556/v1" @default.
- W4386089418 hasPublicationYear "2023" @default.
- W4386089418 type Work @default.
- W4386089418 citedByCount "0" @default.
- W4386089418 crossrefType "posted-content" @default.
- W4386089418 hasAuthorship W4386089418A5061490660 @default.
- W4386089418 hasBestOaLocation W43860894181 @default.
- W4386089418 hasConcept C114614502 @default.
- W4386089418 hasConcept C116058348 @default.
- W4386089418 hasConcept C124101348 @default.
- W4386089418 hasConcept C133667856 @default.
- W4386089418 hasConcept C138111711 @default.
- W4386089418 hasConcept C153180895 @default.
- W4386089418 hasConcept C154945302 @default.
- W4386089418 hasConcept C33923547 @default.
- W4386089418 hasConcept C38652104 @default.
- W4386089418 hasConcept C41008148 @default.
- W4386089418 hasConcept C67388219 @default.
- W4386089418 hasConcept C74193536 @default.
- W4386089418 hasConcept C99138194 @default.
- W4386089418 hasConceptScore W4386089418C114614502 @default.
- W4386089418 hasConceptScore W4386089418C116058348 @default.
- W4386089418 hasConceptScore W4386089418C124101348 @default.
- W4386089418 hasConceptScore W4386089418C133667856 @default.
- W4386089418 hasConceptScore W4386089418C138111711 @default.
- W4386089418 hasConceptScore W4386089418C153180895 @default.
- W4386089418 hasConceptScore W4386089418C154945302 @default.
- W4386089418 hasConceptScore W4386089418C33923547 @default.
- W4386089418 hasConceptScore W4386089418C38652104 @default.
- W4386089418 hasConceptScore W4386089418C41008148 @default.
- W4386089418 hasConceptScore W4386089418C67388219 @default.
- W4386089418 hasConceptScore W4386089418C74193536 @default.
- W4386089418 hasConceptScore W4386089418C99138194 @default.
- W4386089418 hasLocation W43860894181 @default.
- W4386089418 hasOpenAccess W4386089418 @default.
- W4386089418 hasPrimaryLocation W43860894181 @default.
- W4386089418 hasRelatedWork W102859714 @default.
- W4386089418 hasRelatedWork W1968923698 @default.
- W4386089418 hasRelatedWork W1972853352 @default.
- W4386089418 hasRelatedWork W2000284985 @default.
- W4386089418 hasRelatedWork W2088296667 @default.
- W4386089418 hasRelatedWork W2171626009 @default.
- W4386089418 hasRelatedWork W2783286101 @default.