FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285308876> ?p ?o ?g. }

• W4285308876 endingPage "1" @default.
• W4285308876 startingPage "1" @default.
• W4285308876 abstract "Owing to its query and storage efficiency, hash learning has sparked much interest for Cross-Modal Retrieval (CMR) task. Previous literatures have proved the superiority of supervised Cross-Modal Hashing (CMH) methods over unsupervised ones. Nevertheless, most existing supervised CMH methods still suffer from some limitations: 1) it is assumed that the observed labels of training data are complete and accurate, which may be impractical due to the missing and wrong class assignments in real applications, and 2) the semantic information is not fully excavated, especially for the semantic correlations among labels. To address these issues, this paper proposes a Weakly-supervised enhAnced Semantic-aware Hashing (WASH) method which simultaneously estimates the label noises and performs enhanced semantic-aware hash learning. WASH employs the low-rank and sparse decomposition to alleviate the label noises, and a high-level semantic factor as well as a semantic correlation matrix is obtained by low-rank factorization on the noise-reduced labels. The low-rank semantic factors and multi-modal features are jointly factorized into a common subspace to reduce the heterogeneity gaps, so as to enhance the semantic awareness of shared representation. In this way, the hash codes can be obtained by binarizing the shared representation with pairwise semantic similarity preserved. Experiments on several benchmark datasets verify the effectiveness of the proposed method in comparison with the state-of-the-art CMH approaches." @default.
• W4285308876 created "2022-07-14" @default.
• W4285308876 creator A5047526614 @default.
• W4285308876 creator A5074250521 @default.
• W4285308876 creator A5076835782 @default.
• W4285308876 creator A5089966579 @default.
• W4285308876 date "2022-01-01" @default.
• W4285308876 modified "2023-10-15" @default.
• W4285308876 title "Weakly-Supervised Enhanced Semantic-Aware Hashing for Cross-Modal Retrieval" @default.
• W4285308876 cites W1922199343 @default.
• W4285308876 cites W2006147162 @default.
• W4285308876 cites W2007972815 @default.
• W4285308876 cites W2118550318 @default.
• W4285308876 cites W2203543769 @default.
• W4285308876 cites W2266728343 @default.
• W4285308876 cites W2512032049 @default.
• W4285308876 cites W2568737927 @default.
• W4285308876 cites W2591669147 @default.
• W4285308876 cites W2604880013 @default.
• W4285308876 cites W2605997098 @default.
• W4285308876 cites W2606965845 @default.
• W4285308876 cites W2725249286 @default.
• W4285308876 cites W2746791238 @default.
• W4285308876 cites W2766247310 @default.
• W4285308876 cites W2788843501 @default.
• W4285308876 cites W2802864907 @default.
• W4285308876 cites W2889212689 @default.
• W4285308876 cites W2898233200 @default.
• W4285308876 cites W2903903916 @default.
• W4285308876 cites W2904572180 @default.
• W4285308876 cites W2907166662 @default.
• W4285308876 cites W2922521335 @default.
• W4285308876 cites W2940532918 @default.
• W4285308876 cites W2945578092 @default.
• W4285308876 cites W2949483514 @default.
• W4285308876 cites W2962955826 @default.
• W4285308876 cites W2971949219 @default.
• W4285308876 cites W2981777726 @default.
• W4285308876 cites W2989562653 @default.
• W4285308876 cites W3003735286 @default.
• W4285308876 cites W3017133364 @default.
• W4285308876 cites W3025665229 @default.
• W4285308876 cites W3034890701 @default.
• W4285308876 cites W3035485997 @default.
• W4285308876 cites W3090449556 @default.
• W4285308876 cites W3094095292 @default.
• W4285308876 cites W3111322046 @default.
• W4285308876 cites W3136345137 @default.
• W4285308876 cites W3162085601 @default.
• W4285308876 cites W3170038038 @default.
• W4285308876 cites W3176451698 @default.
• W4285308876 cites W3192393047 @default.
• W4285308876 cites W3199266039 @default.
• W4285308876 doi "https://doi.org/10.1109/tkde.2022.3172216" @default.
• W4285308876 hasPublicationYear "2022" @default.
• W4285308876 type Work @default.
• W4285308876 citedByCount "4" @default.
• W4285308876 countsByYear W42853088762022 @default.
• W4285308876 countsByYear W42853088762023 @default.
• W4285308876 crossrefType "journal-article" @default.
• W4285308876 hasAuthorship W4285308876A5047526614 @default.
• W4285308876 hasAuthorship W4285308876A5074250521 @default.
• W4285308876 hasAuthorship W4285308876A5076835782 @default.
• W4285308876 hasAuthorship W4285308876A5089966579 @default.
• W4285308876 hasConcept C114614502 @default.
• W4285308876 hasConcept C115961682 @default.
• W4285308876 hasConcept C119857082 @default.
• W4285308876 hasConcept C121332964 @default.
• W4285308876 hasConcept C124101348 @default.
• W4285308876 hasConcept C130318100 @default.
• W4285308876 hasConcept C13280743 @default.
• W4285308876 hasConcept C133667856 @default.
• W4285308876 hasConcept C138111711 @default.
• W4285308876 hasConcept C153180895 @default.
• W4285308876 hasConcept C154945302 @default.
• W4285308876 hasConcept C157659113 @default.
• W4285308876 hasConcept C158693339 @default.
• W4285308876 hasConcept C164226766 @default.
• W4285308876 hasConcept C1667742 @default.
• W4285308876 hasConcept C185798385 @default.
• W4285308876 hasConcept C205649164 @default.
• W4285308876 hasConcept C23123220 @default.
• W4285308876 hasConcept C33923547 @default.
• W4285308876 hasConcept C38652104 @default.
• W4285308876 hasConcept C41008148 @default.
• W4285308876 hasConcept C42355184 @default.
• W4285308876 hasConcept C62520636 @default.
• W4285308876 hasConcept C67388219 @default.
• W4285308876 hasConcept C86034646 @default.
• W4285308876 hasConcept C99138194 @default.
• W4285308876 hasConceptScore W4285308876C114614502 @default.
• W4285308876 hasConceptScore W4285308876C115961682 @default.
• W4285308876 hasConceptScore W4285308876C119857082 @default.
• W4285308876 hasConceptScore W4285308876C121332964 @default.
• W4285308876 hasConceptScore W4285308876C124101348 @default.
• W4285308876 hasConceptScore W4285308876C130318100 @default.
• W4285308876 hasConceptScore W4285308876C13280743 @default.
• W4285308876 hasConceptScore W4285308876C133667856 @default.

• next