Matches in SemOpenAlex for { <https://semopenalex.org/work/W2806203604> ?p ?o ?g. }
- W2806203604 endingPage "85" @default.
- W2806203604 startingPage "75" @default.
- W2806203604 abstract "Abstract With the prevalent use of mobile cameras to capture images, the demands for efficient and effective methods for indexing and retrieval of personal image collections on mobile devices have also risen. In this paper, we propose to represent images with hash codes, which is a compressed representation of deep convolutional features using deep auto-encoder on the cloud. To ensure user's privacy, the image is first encrypted using a light-weight encryption algorithm on mobile device prior to offloading it to the cloud for features extraction. This approach eliminates the computationally expensive process of features extraction on resource constrained devices. A pre-trained convolutional neural network (CNN) is used to extract features which are then transformed to compact binary codes using a deep auto-encoder. The hash codes are then sent back to the mobile device where they are stored in a hash table along with image location. Approximate nearest neighbor (ANN) search approach is utilized to efficiently retrieve the desired images without exhaustive searching of the entire image collection. The proposed method is evaluated against three different publicly available image datasets namely Corel-10K, GHIM-10K, and Product image dataset. Experimental results demonstrate that features representation using CNN and auto-encoder shows much better results than several state-of-the-art hashing schemes for image retrieval on mobile devices." @default.
- W2806203604 created "2018-06-13" @default.
- W2806203604 creator A5004591389 @default.
- W2806203604 creator A5008903140 @default.
- W2806203604 creator A5034370634 @default.
- W2806203604 creator A5072241102 @default.
- W2806203604 date "2018-09-01" @default.
- W2806203604 modified "2023-09-27" @default.
- W2806203604 title "Privacy-preserving image retrieval for mobile devices with deep features on the cloud" @default.
- W2806203604 cites W1787484557 @default.
- W2806203604 cites W1974647172 @default.
- W2806203604 cites W1979493600 @default.
- W2806203604 cites W1990537115 @default.
- W2806203604 cites W2001773889 @default.
- W2806203604 cites W2007877577 @default.
- W2806203604 cites W2020498246 @default.
- W2806203604 cites W2040918046 @default.
- W2806203604 cites W2056105196 @default.
- W2806203604 cites W2061879449 @default.
- W2806203604 cites W2075547840 @default.
- W2806203604 cites W2099739670 @default.
- W2806203604 cites W2119605622 @default.
- W2806203604 cites W2121948167 @default.
- W2806203604 cites W2124404372 @default.
- W2806203604 cites W2127766487 @default.
- W2806203604 cites W2128543433 @default.
- W2806203604 cites W2145426052 @default.
- W2806203604 cites W2147141800 @default.
- W2806203604 cites W2151103935 @default.
- W2806203604 cites W2164131468 @default.
- W2806203604 cites W2168692016 @default.
- W2806203604 cites W2170410701 @default.
- W2806203604 cites W2225750049 @default.
- W2806203604 cites W2323473128 @default.
- W2806203604 cites W2329582438 @default.
- W2806203604 cites W2474846563 @default.
- W2806203604 cites W2490265015 @default.
- W2806203604 cites W2551235116 @default.
- W2806203604 cites W2556162128 @default.
- W2806203604 cites W2604541107 @default.
- W2806203604 cites W2610685678 @default.
- W2806203604 cites W2613554997 @default.
- W2806203604 cites W2742991414 @default.
- W2806203604 cites W2767690801 @default.
- W2806203604 cites W2770141764 @default.
- W2806203604 cites W2770736290 @default.
- W2806203604 cites W2779880100 @default.
- W2806203604 cites W2783430431 @default.
- W2806203604 cites W2789621530 @default.
- W2806203604 cites W2790757012 @default.
- W2806203604 cites W2963213486 @default.
- W2806203604 doi "https://doi.org/10.1016/j.comcom.2018.06.001" @default.
- W2806203604 hasPublicationYear "2018" @default.
- W2806203604 type Work @default.
- W2806203604 sameAs 2806203604 @default.
- W2806203604 citedByCount "24" @default.
- W2806203604 countsByYear W28062036042019 @default.
- W2806203604 countsByYear W28062036042020 @default.
- W2806203604 countsByYear W28062036042021 @default.
- W2806203604 countsByYear W28062036042022 @default.
- W2806203604 countsByYear W28062036042023 @default.
- W2806203604 crossrefType "journal-article" @default.
- W2806203604 hasAuthorship W2806203604A5004591389 @default.
- W2806203604 hasAuthorship W2806203604A5008903140 @default.
- W2806203604 hasAuthorship W2806203604A5034370634 @default.
- W2806203604 hasAuthorship W2806203604A5072241102 @default.
- W2806203604 hasConcept C111919701 @default.
- W2806203604 hasConcept C115961682 @default.
- W2806203604 hasConcept C136764020 @default.
- W2806203604 hasConcept C154945302 @default.
- W2806203604 hasConcept C1667742 @default.
- W2806203604 hasConcept C186967261 @default.
- W2806203604 hasConcept C23123220 @default.
- W2806203604 hasConcept C31972630 @default.
- W2806203604 hasConcept C38652104 @default.
- W2806203604 hasConcept C41008148 @default.
- W2806203604 hasConcept C79974875 @default.
- W2806203604 hasConceptScore W2806203604C111919701 @default.
- W2806203604 hasConceptScore W2806203604C115961682 @default.
- W2806203604 hasConceptScore W2806203604C136764020 @default.
- W2806203604 hasConceptScore W2806203604C154945302 @default.
- W2806203604 hasConceptScore W2806203604C1667742 @default.
- W2806203604 hasConceptScore W2806203604C186967261 @default.
- W2806203604 hasConceptScore W2806203604C23123220 @default.
- W2806203604 hasConceptScore W2806203604C31972630 @default.
- W2806203604 hasConceptScore W2806203604C38652104 @default.
- W2806203604 hasConceptScore W2806203604C41008148 @default.
- W2806203604 hasConceptScore W2806203604C79974875 @default.
- W2806203604 hasFunder F4320322120 @default.
- W2806203604 hasLocation W28062036041 @default.
- W2806203604 hasOpenAccess W2806203604 @default.
- W2806203604 hasPrimaryLocation W28062036041 @default.
- W2806203604 hasRelatedWork W1536471031 @default.
- W2806203604 hasRelatedWork W1542642427 @default.
- W2806203604 hasRelatedWork W1606646991 @default.
- W2806203604 hasRelatedWork W2005185696 @default.
- W2806203604 hasRelatedWork W2130228941 @default.
- W2806203604 hasRelatedWork W2161229648 @default.