FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2892948265> ?p ?o ?g. }

• W2892948265 endingPage "1193" @default.
• W2892948265 startingPage "1181" @default.
• W2892948265 abstract "Steganography detectors built as deep convolutional neural networks have firmly established themselves as superior to the previous detection paradigm - classifiers based on rich media models. Existing network architectures, however, still contain elements designed by hand, such as fixed or constrained convolutional kernels, heuristic initialization of kernels, the thresholded linear unit that mimics truncation in rich models, quantization of feature maps, and awareness of JPEG phase. In this work, we describe a deep residual architecture designed to minimize the use of heuristics and externally enforced elements that is universal in the sense that it provides state-of-the-art detection accuracy for both spatial-domain and JPEG steganography. The key part of the proposed architecture is a significantly expanded front part of the detector that “computes noise residuals” in which pooling has been disabled to prevent suppression of the stego signal. Extensive experiments show the superior performance of this network with a significant improvement, especially in the JPEG domain. Further performance boost is observed by supplying the selection channel as a second channel." @default.
• W2892948265 created "2018-10-05" @default.
• W2892948265 creator A5043858190 @default.
• W2892948265 creator A5075476512 @default.
• W2892948265 creator A5081020569 @default.
• W2892948265 date "2019-05-01" @default.
• W2892948265 modified "2023-10-14" @default.
• W2892948265 title "Deep Residual Network for Steganalysis of Digital Images" @default.
• W2892948265 cites W10162706 @default.
• W2892948265 cites W1422592601 @default.
• W2892948265 cites W1658688950 @default.
• W2892948265 cites W1973466159 @default.
• W2892948265 cites W1976570511 @default.
• W2892948265 cites W2009130368 @default.
• W2892948265 cites W2023556846 @default.
• W2892948265 cites W2031466562 @default.
• W2892948265 cites W2032317389 @default.
• W2892948265 cites W2040953223 @default.
• W2892948265 cites W2045110448 @default.
• W2892948265 cites W2046180645 @default.
• W2892948265 cites W2050843048 @default.
• W2892948265 cites W2055625960 @default.
• W2892948265 cites W2059019537 @default.
• W2892948265 cites W2061397706 @default.
• W2892948265 cites W2071451750 @default.
• W2892948265 cites W2081564928 @default.
• W2892948265 cites W2104705565 @default.
• W2892948265 cites W2105317222 @default.
• W2892948265 cites W2117539524 @default.
• W2892948265 cites W2121585984 @default.
• W2892948265 cites W2124664712 @default.
• W2892948265 cites W2136492908 @default.
• W2892948265 cites W2136744314 @default.
• W2892948265 cites W2170311913 @default.
• W2892948265 cites W2170598445 @default.
• W2892948265 cites W2192227561 @default.
• W2892948265 cites W2194775991 @default.
• W2892948265 cites W2277839806 @default.
• W2892948265 cites W2296073425 @default.
• W2892948265 cites W2322622188 @default.
• W2892948265 cites W2339370745 @default.
• W2892948265 cites W2416075718 @default.
• W2892948265 cites W2417217221 @default.
• W2892948265 cites W2538511122 @default.
• W2892948265 cites W2539782905 @default.
• W2892948265 cites W2542290803 @default.
• W2892948265 cites W2545848843 @default.
• W2892948265 cites W2565257220 @default.
• W2892948265 cites W2571946726 @default.
• W2892948265 cites W2579698629 @default.
• W2892948265 cites W2610979719 @default.
• W2892948265 cites W2621048556 @default.
• W2892948265 cites W2735904389 @default.
• W2892948265 cites W2736102651 @default.
• W2892948265 cites W2736148246 @default.
• W2892948265 cites W2739185626 @default.
• W2892948265 cites W2751202750 @default.
• W2892948265 cites W2963446712 @default.
• W2892948265 cites W3142078075 @default.
• W2892948265 doi "https://doi.org/10.1109/tifs.2018.2871749" @default.
• W2892948265 hasPublicationYear "2019" @default.
• W2892948265 type Work @default.
• W2892948265 sameAs 2892948265 @default.
• W2892948265 citedByCount "428" @default.
• W2892948265 countsByYear W28929482652012 @default.
• W2892948265 countsByYear W28929482652019 @default.
• W2892948265 countsByYear W28929482652020 @default.
• W2892948265 countsByYear W28929482652021 @default.
• W2892948265 countsByYear W28929482652022 @default.
• W2892948265 countsByYear W28929482652023 @default.
• W2892948265 crossrefType "journal-article" @default.
• W2892948265 hasAuthorship W2892948265A5043858190 @default.
• W2892948265 hasAuthorship W2892948265A5075476512 @default.
• W2892948265 hasAuthorship W2892948265A5081020569 @default.
• W2892948265 hasBestOaLocation W28929482651 @default.
• W2892948265 hasConcept C107368093 @default.
• W2892948265 hasConcept C108801101 @default.
• W2892948265 hasConcept C11413529 @default.
• W2892948265 hasConcept C153180895 @default.
• W2892948265 hasConcept C154945302 @default.
• W2892948265 hasConcept C155512373 @default.
• W2892948265 hasConcept C198751489 @default.
• W2892948265 hasConcept C28855332 @default.
• W2892948265 hasConcept C31972630 @default.
• W2892948265 hasConcept C41008148 @default.
• W2892948265 hasConcept C41608201 @default.
• W2892948265 hasConcept C78548338 @default.
• W2892948265 hasConcept C81363708 @default.
• W2892948265 hasConceptScore W2892948265C107368093 @default.
• W2892948265 hasConceptScore W2892948265C108801101 @default.
• W2892948265 hasConceptScore W2892948265C11413529 @default.
• W2892948265 hasConceptScore W2892948265C153180895 @default.
• W2892948265 hasConceptScore W2892948265C154945302 @default.
• W2892948265 hasConceptScore W2892948265C155512373 @default.
• W2892948265 hasConceptScore W2892948265C198751489 @default.
• W2892948265 hasConceptScore W2892948265C28855332 @default.
• W2892948265 hasConceptScore W2892948265C31972630 @default.
• W2892948265 hasConceptScore W2892948265C41008148 @default.

• next