Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293843080> ?p ?o ?g. }
- W4293843080 endingPage "4327" @default.
- W4293843080 startingPage "4295" @default.
- W4293843080 abstract "As neural networks become able to generate realistic artificial images, they have the potential to improve movies, music, video games and make the internet an even more creative and inspiring place. Yet, the latest technology potentially enables new digital ways to lie. In response, the need for a diverse and reliable method toolbox arises to identify artificial images and other content. Previous work primarily relies on pixel-space CNNs or the Fourier transform. To the best of our knowledge, synthesized fake image analysis and detection methods based on a multi-scale wavelet representation, localized in both space and frequency, have been absent thus far. The wavelet transform conserves spatial information to a degree, which allows us to present a new analysis. Comparing the wavelet coefficients of real and fake images allows interpretation. Significant differences are identified. Additionally, this paper proposes to learn a model for the detection of synthetic images based on the wavelet-packet representation of natural and GAN-generated images. Our lightweight forensic classifiers exhibit competitive or improved performance at comparatively small network sizes, as we demonstrate on the FFHQ, CelebA and LSUN source identification problems. Furthermore, we study the binary FaceForensics++ fake-detection problem." @default.
- W4293843080 created "2022-08-31" @default.
- W4293843080 creator A5002790877 @default.
- W4293843080 creator A5019819029 @default.
- W4293843080 creator A5029156019 @default.
- W4293843080 creator A5068763843 @default.
- W4293843080 date "2022-08-31" @default.
- W4293843080 modified "2023-09-28" @default.
- W4293843080 title "Wavelet-packets for deepfake image analysis and detection" @default.
- W4293843080 cites W1834627138 @default.
- W4293843080 cites W1932922755 @default.
- W4293843080 cites W1994906459 @default.
- W4293843080 cites W2009130368 @default.
- W4293843080 cites W2072072671 @default.
- W4293843080 cites W2098386213 @default.
- W4293843080 cites W2105581333 @default.
- W4293843080 cites W2130259898 @default.
- W4293843080 cites W2132984323 @default.
- W4293843080 cites W227339781 @default.
- W4293843080 cites W2301937176 @default.
- W4293843080 cites W2412509443 @default.
- W4293843080 cites W2475287302 @default.
- W4293843080 cites W2531409750 @default.
- W4293843080 cites W2587706859 @default.
- W4293843080 cites W2603123944 @default.
- W4293843080 cites W2773863050 @default.
- W4293843080 cites W2786289897 @default.
- W4293843080 cites W2891145043 @default.
- W4293843080 cites W2907295878 @default.
- W4293843080 cites W2942074357 @default.
- W4293843080 cites W2962770929 @default.
- W4293843080 cites W2982058372 @default.
- W4293843080 cites W2991318208 @default.
- W4293843080 cites W3012472557 @default.
- W4293843080 cites W3034214108 @default.
- W4293843080 cites W3034577585 @default.
- W4293843080 cites W3034864980 @default.
- W4293843080 cites W3035574324 @default.
- W4293843080 cites W3043392332 @default.
- W4293843080 cites W3048007723 @default.
- W4293843080 cites W3122852338 @default.
- W4293843080 cites W3143942160 @default.
- W4293843080 cites W3174508664 @default.
- W4293843080 cites W3174814557 @default.
- W4293843080 cites W3181955432 @default.
- W4293843080 cites W3187526215 @default.
- W4293843080 cites W3216759837 @default.
- W4293843080 cites W4205695807 @default.
- W4293843080 cites W4214680478 @default.
- W4293843080 cites W4255272544 @default.
- W4293843080 doi "https://doi.org/10.1007/s10994-022-06225-5" @default.
- W4293843080 hasPublicationYear "2022" @default.
- W4293843080 type Work @default.
- W4293843080 citedByCount "5" @default.
- W4293843080 countsByYear W42938430802023 @default.
- W4293843080 crossrefType "journal-article" @default.
- W4293843080 hasAuthorship W4293843080A5002790877 @default.
- W4293843080 hasAuthorship W4293843080A5019819029 @default.
- W4293843080 hasAuthorship W4293843080A5029156019 @default.
- W4293843080 hasAuthorship W4293843080A5068763843 @default.
- W4293843080 hasBestOaLocation W42938430801 @default.
- W4293843080 hasConcept C115961682 @default.
- W4293843080 hasConcept C153180895 @default.
- W4293843080 hasConcept C154945302 @default.
- W4293843080 hasConcept C155777637 @default.
- W4293843080 hasConcept C17744445 @default.
- W4293843080 hasConcept C196216189 @default.
- W4293843080 hasConcept C199539241 @default.
- W4293843080 hasConcept C2776359362 @default.
- W4293843080 hasConcept C31972630 @default.
- W4293843080 hasConcept C41008148 @default.
- W4293843080 hasConcept C47432892 @default.
- W4293843080 hasConcept C94625758 @default.
- W4293843080 hasConceptScore W4293843080C115961682 @default.
- W4293843080 hasConceptScore W4293843080C153180895 @default.
- W4293843080 hasConceptScore W4293843080C154945302 @default.
- W4293843080 hasConceptScore W4293843080C155777637 @default.
- W4293843080 hasConceptScore W4293843080C17744445 @default.
- W4293843080 hasConceptScore W4293843080C196216189 @default.
- W4293843080 hasConceptScore W4293843080C199539241 @default.
- W4293843080 hasConceptScore W4293843080C2776359362 @default.
- W4293843080 hasConceptScore W4293843080C31972630 @default.
- W4293843080 hasConceptScore W4293843080C41008148 @default.
- W4293843080 hasConceptScore W4293843080C47432892 @default.
- W4293843080 hasConceptScore W4293843080C94625758 @default.
- W4293843080 hasFunder F4320321773 @default.
- W4293843080 hasFunder F4320324900 @default.
- W4293843080 hasIssue "11" @default.
- W4293843080 hasLocation W42938430801 @default.
- W4293843080 hasLocation W42938430802 @default.
- W4293843080 hasLocation W42938430803 @default.
- W4293843080 hasOpenAccess W4293843080 @default.
- W4293843080 hasPrimaryLocation W42938430801 @default.
- W4293843080 hasRelatedWork W1502966458 @default.
- W4293843080 hasRelatedWork W1577789985 @default.
- W4293843080 hasRelatedWork W2041988345 @default.
- W4293843080 hasRelatedWork W2047056993 @default.
- W4293843080 hasRelatedWork W2085792030 @default.