FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2802516677> ?p ?o ?g. }

• W2802516677 endingPage "27102" @default.
• W2802516677 startingPage "27091" @default.
• W2802516677 abstract "Most existing cross-modal retrieval approaches learn the same couple of projection matrices for different sub-retrieval tasks (such as, image retrieves text and text retrieves image) and various queries. They ignore the important fact that, different sub-retrieval tasks and queries have unique characteristics themselves in real practice. To tackle the problem, we propose a task-dependent and query-dependent subspace learning approach for cross-modal retrieval. Specifically, we first develop a unified cross-modal learning framework, where task-specific and category-specific subspaces can be learned simultaneously via an efficient iterative optimization. Based on this step, a task-category-projection mapping table is built. Subsequently, an efficient linear classifier is trained to learn a semantic mapping function between multimedia documents and their potential categories. In the online retrieval stage, the task-dependent and query-dependent matching subspace is adaptively identified by considering the specific sub-retrieval task type, the potential semantic category of the query, and the task-category-projection mapping table. Experimental results demonstrate the superior performance of the proposed approach compared with several state-of-the-art techniques." @default.
• W2802516677 created "2018-05-17" @default.
• W2802516677 creator A5012278873 @default.
• W2802516677 creator A5036777291 @default.
• W2802516677 creator A5051630734 @default.
• W2802516677 creator A5072520382 @default.
• W2802516677 creator A5080244427 @default.
• W2802516677 date "2018-01-01" @default.
• W2802516677 modified "2023-10-16" @default.
• W2802516677 title "Task-Dependent and Query-Dependent Subspace Learning for Cross-Modal Retrieval" @default.
• W2802516677 cites W1123427201 @default.
• W2802516677 cites W1967643748 @default.
• W2802516677 cites W2022398331 @default.
• W2802516677 cites W2030507150 @default.
• W2802516677 cites W2030899956 @default.
• W2802516677 cites W2035821475 @default.
• W2802516677 cites W2059003682 @default.
• W2802516677 cites W2070753207 @default.
• W2802516677 cites W2071207147 @default.
• W2802516677 cites W2089549033 @default.
• W2802516677 cites W2106277773 @default.
• W2802516677 cites W2114661696 @default.
• W2802516677 cites W2117946510 @default.
• W2802516677 cites W2119046205 @default.
• W2802516677 cites W2140406904 @default.
• W2802516677 cites W2163740729 @default.
• W2802516677 cites W2164530430 @default.
• W2802516677 cites W2210322478 @default.
• W2802516677 cites W2211092169 @default.
• W2802516677 cites W2246035736 @default.
• W2802516677 cites W2274047922 @default.
• W2802516677 cites W2282231212 @default.
• W2802516677 cites W2326180695 @default.
• W2802516677 cites W2327894203 @default.
• W2802516677 cites W2345649690 @default.
• W2802516677 cites W2345812103 @default.
• W2802516677 cites W2411707397 @default.
• W2802516677 cites W2414522539 @default.
• W2802516677 cites W2513281263 @default.
• W2802516677 cites W2520861906 @default.
• W2802516677 cites W2534014507 @default.
• W2802516677 cites W2585022092 @default.
• W2802516677 cites W2605187330 @default.
• W2802516677 cites W2619145493 @default.
• W2802516677 cites W2626052180 @default.
• W2802516677 cites W2725249286 @default.
• W2802516677 cites W2739107216 @default.
• W2802516677 cites W2756217268 @default.
• W2802516677 cites W2767073696 @default.
• W2802516677 cites W2793456900 @default.
• W2802516677 cites W2963634791 @default.
• W2802516677 doi "https://doi.org/10.1109/access.2018.2831675" @default.
• W2802516677 hasPublicationYear "2018" @default.
• W2802516677 type Work @default.
• W2802516677 sameAs 2802516677 @default.
• W2802516677 citedByCount "11" @default.
• W2802516677 countsByYear W28025166772019 @default.
• W2802516677 countsByYear W28025166772020 @default.
• W2802516677 countsByYear W28025166772021 @default.
• W2802516677 countsByYear W28025166772022 @default.
• W2802516677 countsByYear W28025166772023 @default.
• W2802516677 crossrefType "journal-article" @default.
• W2802516677 hasAuthorship W2802516677A5012278873 @default.
• W2802516677 hasAuthorship W2802516677A5036777291 @default.
• W2802516677 hasAuthorship W2802516677A5051630734 @default.
• W2802516677 hasAuthorship W2802516677A5072520382 @default.
• W2802516677 hasAuthorship W2802516677A5080244427 @default.
• W2802516677 hasBestOaLocation W28025166771 @default.
• W2802516677 hasConcept C11413529 @default.
• W2802516677 hasConcept C12362212 @default.
• W2802516677 hasConcept C153180895 @default.
• W2802516677 hasConcept C154945302 @default.
• W2802516677 hasConcept C162324750 @default.
• W2802516677 hasConcept C185592680 @default.
• W2802516677 hasConcept C187736073 @default.
• W2802516677 hasConcept C188027245 @default.
• W2802516677 hasConcept C23123220 @default.
• W2802516677 hasConcept C2524010 @default.
• W2802516677 hasConcept C2780451532 @default.
• W2802516677 hasConcept C32834561 @default.
• W2802516677 hasConcept C33923547 @default.
• W2802516677 hasConcept C41008148 @default.
• W2802516677 hasConcept C57493831 @default.
• W2802516677 hasConcept C71139939 @default.
• W2802516677 hasConcept C95623464 @default.
• W2802516677 hasConceptScore W2802516677C11413529 @default.
• W2802516677 hasConceptScore W2802516677C12362212 @default.
• W2802516677 hasConceptScore W2802516677C153180895 @default.
• W2802516677 hasConceptScore W2802516677C154945302 @default.
• W2802516677 hasConceptScore W2802516677C162324750 @default.
• W2802516677 hasConceptScore W2802516677C185592680 @default.
• W2802516677 hasConceptScore W2802516677C187736073 @default.
• W2802516677 hasConceptScore W2802516677C188027245 @default.
• W2802516677 hasConceptScore W2802516677C23123220 @default.
• W2802516677 hasConceptScore W2802516677C2524010 @default.
• W2802516677 hasConceptScore W2802516677C2780451532 @default.
• W2802516677 hasConceptScore W2802516677C32834561 @default.
• W2802516677 hasConceptScore W2802516677C33923547 @default.

• next