FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3103671489> ?p ?o ?g. }

• W3103671489 endingPage "4092" @default.
• W3103671489 startingPage "4079" @default.
• W3103671489 abstract "Social networks allow users to actively upload images and descriptive tags, which has led to an explosive growth in the number of social images. Multi-view hashing is an efficient technique for supporting large-scale social image retrieval because of its desirable capabilities of encoding multi-view features into compact binary hash codes with extremely low storage costs and fast retrieval speeds. However, existing methods require multi-view features to be fully paired at both the offline model training and online query stages. This requirement cannot be easily satisfied for social image retrieval, where social images that lack descriptive tags are common in social networks. In this paper, we propose an <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Unsupervised Adaptive Partial Multi-view Hashing</i> (UAPMH) method to handle the partial-view hashing problem for efficient social image retrieval. Specifically, the shared and view-specific latent representations of fully paired and partial-view images, respectively, are learned separately by an adaptive partial multi-view matrix factorization module within the identical semantic space. In particular, instead of adopting simple fixed view combination weights, we develop a parameter-free weight learning scheme to adaptively learn the weights to capture the view variations and the discriminative capabilities of different views. With such a design, our model can sufficiently exploit the available partial-view samples with separate hash code learning and effectively preserve the latent relations of images and tags in hash codes with semantic space sharing. Moreover, to avoid relaxing errors and improve the learning efficiency, binary hash codes are directly learned in a fast mode with simple and efficient operations. Finally, we extend UAPMH to the supervised learning paradigm as <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Supervised Adaptive Partial Multi-view Hashing</i> (SAPMH) with the supervision of pair-wise semantic labels to further enhance the discriminative capability of hash codes. The experiments demonstrate the state-of-the-art performance of the proposed approaches on public social image retrieval datasets. Our source codes and testing datasets can be obtained at <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://github.com/ChaoqunZheng/APMH</uri> ." @default.
• W3103671489 created "2020-11-23" @default.
• W3103671489 creator A5013617878 @default.
• W3103671489 creator A5026738854 @default.
• W3103671489 creator A5051630734 @default.
• W3103671489 creator A5068843001 @default.
• W3103671489 creator A5081485810 @default.
• W3103671489 date "2021-01-01" @default.
• W3103671489 modified "2023-10-16" @default.
• W3103671489 title "Adaptive Partial Multi-View Hashing for Efficient Social Image Retrieval" @default.
• W3103671489 cites W1880723540 @default.
• W3103671489 cites W1910300841 @default.
• W3103671489 cites W1969752030 @default.
• W3103671489 cites W1974647172 @default.
• W3103671489 cites W1996936615 @default.
• W3103671489 cites W2007972815 @default.
• W3103671489 cites W2025432722 @default.
• W3103671489 cites W2026669354 @default.
• W3103671489 cites W2038233937 @default.
• W3103671489 cites W2079202281 @default.
• W3103671489 cites W2093932377 @default.
• W3103671489 cites W2155803963 @default.
• W3103671489 cites W2162670057 @default.
• W3103671489 cites W2167451801 @default.
• W3103671489 cites W2266728343 @default.
• W3103671489 cites W2519051215 @default.
• W3103671489 cites W2582558662 @default.
• W3103671489 cites W2589266112 @default.
• W3103671489 cites W2591669147 @default.
• W3103671489 cites W2620123979 @default.
• W3103671489 cites W2624945720 @default.
• W3103671489 cites W2752197020 @default.
• W3103671489 cites W2793456900 @default.
• W3103671489 cites W2799214875 @default.
• W3103671489 cites W2805087257 @default.
• W3103671489 cites W2807944281 @default.
• W3103671489 cites W2808282156 @default.
• W3103671489 cites W2891193211 @default.
• W3103671489 cites W2896826707 @default.
• W3103671489 cites W2955273087 @default.
• W3103671489 cites W2962955826 @default.
• W3103671489 cites W2962977389 @default.
• W3103671489 cites W2963634791 @default.
• W3103671489 cites W2974497444 @default.
• W3103671489 cites W2976061040 @default.
• W3103671489 cites W2981076146 @default.
• W3103671489 cites W3006683596 @default.
• W3103671489 cites W3008014442 @default.
• W3103671489 cites W3105204788 @default.
• W3103671489 doi "https://doi.org/10.1109/tmm.2020.3037456" @default.
• W3103671489 hasPublicationYear "2021" @default.
• W3103671489 type Work @default.
• W3103671489 sameAs 3103671489 @default.
• W3103671489 citedByCount "11" @default.
• W3103671489 countsByYear W31036714892021 @default.
• W3103671489 countsByYear W31036714892022 @default.
• W3103671489 countsByYear W31036714892023 @default.
• W3103671489 crossrefType "journal-article" @default.
• W3103671489 hasAuthorship W3103671489A5013617878 @default.
• W3103671489 hasAuthorship W3103671489A5026738854 @default.
• W3103671489 hasAuthorship W3103671489A5051630734 @default.
• W3103671489 hasAuthorship W3103671489A5068843001 @default.
• W3103671489 hasAuthorship W3103671489A5081485810 @default.
• W3103671489 hasConcept C115961682 @default.
• W3103671489 hasConcept C116058348 @default.
• W3103671489 hasConcept C119857082 @default.
• W3103671489 hasConcept C133667856 @default.
• W3103671489 hasConcept C138111711 @default.
• W3103671489 hasConcept C153180895 @default.
• W3103671489 hasConcept C154945302 @default.
• W3103671489 hasConcept C1667742 @default.
• W3103671489 hasConcept C23123220 @default.
• W3103671489 hasConcept C33923547 @default.
• W3103671489 hasConcept C38652104 @default.
• W3103671489 hasConcept C41008148 @default.
• W3103671489 hasConcept C48372109 @default.
• W3103671489 hasConcept C63435697 @default.
• W3103671489 hasConcept C67388219 @default.
• W3103671489 hasConcept C80444323 @default.
• W3103671489 hasConcept C94375191 @default.
• W3103671489 hasConcept C97931131 @default.
• W3103671489 hasConcept C99138194 @default.
• W3103671489 hasConceptScore W3103671489C115961682 @default.
• W3103671489 hasConceptScore W3103671489C116058348 @default.
• W3103671489 hasConceptScore W3103671489C119857082 @default.
• W3103671489 hasConceptScore W3103671489C133667856 @default.
• W3103671489 hasConceptScore W3103671489C138111711 @default.
• W3103671489 hasConceptScore W3103671489C153180895 @default.
• W3103671489 hasConceptScore W3103671489C154945302 @default.
• W3103671489 hasConceptScore W3103671489C1667742 @default.
• W3103671489 hasConceptScore W3103671489C23123220 @default.
• W3103671489 hasConceptScore W3103671489C33923547 @default.
• W3103671489 hasConceptScore W3103671489C38652104 @default.
• W3103671489 hasConceptScore W3103671489C41008148 @default.
• W3103671489 hasConceptScore W3103671489C48372109 @default.
• W3103671489 hasConceptScore W3103671489C63435697 @default.
• W3103671489 hasConceptScore W3103671489C67388219 @default.
• W3103671489 hasConceptScore W3103671489C80444323 @default.

• next