Matches in SemOpenAlex for { <https://semopenalex.org/work/W2885272854> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2885272854 endingPage "173" @default.
- W2885272854 startingPage "165" @default.
- W2885272854 abstract "Abstract Most existing supervised subspace learning methods use the label information for high-level semantic exploration and learn one couple of common mapping matrices for all classes in the retrieval task. However, there are different semantic distributions among different classes and thus we propose to learn different mapping matrices for different classes in this paper, which facilitates learning more discriminative subspace. In addition, semantic overlap usually exists among different classes, which is reflected through common samples in different classes. Therefore, the multi-class joint subspace learning algorithm (MJSL) is proposed to distinct the different classes and mine the potential shared information of semantic overlap as much as possible. Specifically, the MJSL method considers exploring high-level semantic, keeping pair-wised closeness and selecting optimal features to obtain the most discriminative subspace for each class. Meanwhile, the trace-norm based joint learning is used for exploring the potential shared information of semantic overlap among different classes. Since the optimal mapping matrices have been learned via an iterative joint optimization algorithm with fast convergence, a linear SVM classifier is trained to establish the mapping relationship between multi-modal data and their potential semantic classes. Thus, the most related mapping matrices can be identified for each query adaptively and the retrieval performance can be promoted. Extensive experiments on two popular public datasets demonstrate that our algorithm outperforms several state-of-the-art cross-modal retrieval algorithms." @default.
- W2885272854 created "2018-08-22" @default.
- W2885272854 creator A5012278873 @default.
- W2885272854 creator A5012677271 @default.
- W2885272854 creator A5072520382 @default.
- W2885272854 creator A5077447732 @default.
- W2885272854 creator A5080244427 @default.
- W2885272854 creator A5080617991 @default.
- W2885272854 date "2020-02-01" @default.
- W2885272854 modified "2023-10-16" @default.
- W2885272854 title "Multi-class joint subspace learning for cross-modal retrieval" @default.
- W2885272854 cites W1123427201 @default.
- W2885272854 cites W1970855969 @default.
- W2885272854 cites W1974647172 @default.
- W2885272854 cites W2022398331 @default.
- W2885272854 cites W2055600015 @default.
- W2885272854 cites W2056935845 @default.
- W2885272854 cites W2065180801 @default.
- W2885272854 cites W2070753207 @default.
- W2885272854 cites W2100235303 @default.
- W2885272854 cites W2138118304 @default.
- W2885272854 cites W2170653751 @default.
- W2885272854 cites W2246035736 @default.
- W2885272854 cites W2323115803 @default.
- W2885272854 cites W2520861906 @default.
- W2885272854 cites W2585022092 @default.
- W2885272854 cites W2594785588 @default.
- W2885272854 cites W2625158242 @default.
- W2885272854 cites W2626052180 @default.
- W2885272854 cites W2739250163 @default.
- W2885272854 doi "https://doi.org/10.1016/j.patrec.2018.08.012" @default.
- W2885272854 hasPublicationYear "2020" @default.
- W2885272854 type Work @default.
- W2885272854 sameAs 2885272854 @default.
- W2885272854 citedByCount "6" @default.
- W2885272854 countsByYear W28852728542019 @default.
- W2885272854 countsByYear W28852728542020 @default.
- W2885272854 countsByYear W28852728542022 @default.
- W2885272854 crossrefType "journal-article" @default.
- W2885272854 hasAuthorship W2885272854A5012278873 @default.
- W2885272854 hasAuthorship W2885272854A5012677271 @default.
- W2885272854 hasAuthorship W2885272854A5072520382 @default.
- W2885272854 hasAuthorship W2885272854A5077447732 @default.
- W2885272854 hasAuthorship W2885272854A5080244427 @default.
- W2885272854 hasAuthorship W2885272854A5080617991 @default.
- W2885272854 hasConcept C127413603 @default.
- W2885272854 hasConcept C153180895 @default.
- W2885272854 hasConcept C154945302 @default.
- W2885272854 hasConcept C18555067 @default.
- W2885272854 hasConcept C185592680 @default.
- W2885272854 hasConcept C188027245 @default.
- W2885272854 hasConcept C2777212361 @default.
- W2885272854 hasConcept C32834561 @default.
- W2885272854 hasConcept C33923547 @default.
- W2885272854 hasConcept C41008148 @default.
- W2885272854 hasConcept C66938386 @default.
- W2885272854 hasConcept C71139939 @default.
- W2885272854 hasConceptScore W2885272854C127413603 @default.
- W2885272854 hasConceptScore W2885272854C153180895 @default.
- W2885272854 hasConceptScore W2885272854C154945302 @default.
- W2885272854 hasConceptScore W2885272854C18555067 @default.
- W2885272854 hasConceptScore W2885272854C185592680 @default.
- W2885272854 hasConceptScore W2885272854C188027245 @default.
- W2885272854 hasConceptScore W2885272854C2777212361 @default.
- W2885272854 hasConceptScore W2885272854C32834561 @default.
- W2885272854 hasConceptScore W2885272854C33923547 @default.
- W2885272854 hasConceptScore W2885272854C41008148 @default.
- W2885272854 hasConceptScore W2885272854C66938386 @default.
- W2885272854 hasConceptScore W2885272854C71139939 @default.
- W2885272854 hasFunder F4320321001 @default.
- W2885272854 hasFunder F4320324174 @default.
- W2885272854 hasLocation W28852728541 @default.
- W2885272854 hasOpenAccess W2885272854 @default.
- W2885272854 hasPrimaryLocation W28852728541 @default.
- W2885272854 hasRelatedWork W1510561540 @default.
- W2885272854 hasRelatedWork W1998938004 @default.
- W2885272854 hasRelatedWork W2016349419 @default.
- W2885272854 hasRelatedWork W2119875513 @default.
- W2885272854 hasRelatedWork W2157903613 @default.
- W2885272854 hasRelatedWork W2159633528 @default.
- W2885272854 hasRelatedWork W2167592635 @default.
- W2885272854 hasRelatedWork W2321141263 @default.
- W2885272854 hasRelatedWork W2543161807 @default.
- W2885272854 hasRelatedWork W2164844972 @default.
- W2885272854 hasVolume "130" @default.
- W2885272854 isParatext "false" @default.
- W2885272854 isRetracted "false" @default.
- W2885272854 magId "2885272854" @default.
- W2885272854 workType "article" @default.