Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319296799> ?p ?o ?g. }
- W4319296799 endingPage "816" @default.
- W4319296799 startingPage "816" @default.
- W4319296799 abstract "As deepfake becomes more sophisticated, the demand for fake facial image detection is increasing. Although great progress has been made in deepfake detection, the performance of most existing deepfake detection methods degrade significantly when these methods are applied to detect low-quality images for the disappearance of key clues during the compression process. In this work, we mine frequency domain and RGB domain information to specifically improve the detection of low-quality compressed deepfake images. Our method consists of two modules: (1) a preprocessing module and (2) a classification module. In the preprocessing module, we utilize the Haar wavelet transform and residual calculation to obtain the mid-high frequency joint information and fuse the frequency map with the RGB input. In the classification module, the image obtained by concatenation is fed to the convolutional neural network for classification. Because of the combination of RGB and frequency domain, the robustness of the model has been greatly improved. Our extensive experimental results demonstrate that our approach can not only achieve excellent performance when detecting low-quality compressed deepfake images, but also maintain great performance with high-quality images." @default.
- W4319296799 created "2023-02-07" @default.
- W4319296799 creator A5025599939 @default.
- W4319296799 creator A5032700564 @default.
- W4319296799 creator A5053298425 @default.
- W4319296799 creator A5060520944 @default.
- W4319296799 creator A5061562780 @default.
- W4319296799 creator A5080166226 @default.
- W4319296799 date "2023-02-06" @default.
- W4319296799 modified "2023-09-30" @default.
- W4319296799 title "Frequency Domain Filtered Residual Network for Deepfake Detection" @default.
- W4319296799 cites W1986830331 @default.
- W4319296799 cites W2009130368 @default.
- W4319296799 cites W2097117768 @default.
- W4319296799 cites W2301937176 @default.
- W4319296799 cites W2412509443 @default.
- W4319296799 cites W2531409750 @default.
- W4319296799 cites W2603123944 @default.
- W4319296799 cites W2786289897 @default.
- W4319296799 cites W2891145043 @default.
- W4319296799 cites W2909336075 @default.
- W4319296799 cites W2913399670 @default.
- W4319296799 cites W2914057590 @default.
- W4319296799 cites W2914447220 @default.
- W4319296799 cites W2942074357 @default.
- W4319296799 cites W2963684180 @default.
- W4319296799 cites W2963720850 @default.
- W4319296799 cites W2982058372 @default.
- W4319296799 cites W3017837134 @default.
- W4319296799 cites W3034713808 @default.
- W4319296799 cites W3035063907 @default.
- W4319296799 cites W3036644531 @default.
- W4319296799 cites W3102988878 @default.
- W4319296799 cites W3114370481 @default.
- W4319296799 cites W3132645184 @default.
- W4319296799 cites W3134377386 @default.
- W4319296799 cites W3135413014 @default.
- W4319296799 cites W3158766194 @default.
- W4319296799 cites W3166873596 @default.
- W4319296799 cites W3173631964 @default.
- W4319296799 cites W3174508664 @default.
- W4319296799 cites W3174656926 @default.
- W4319296799 cites W3175342695 @default.
- W4319296799 cites W3176241004 @default.
- W4319296799 cites W3183999072 @default.
- W4319296799 cites W3188897163 @default.
- W4319296799 cites W3191630110 @default.
- W4319296799 cites W3203673582 @default.
- W4319296799 cites W4200551480 @default.
- W4319296799 cites W4251712421 @default.
- W4319296799 cites W4309284213 @default.
- W4319296799 doi "https://doi.org/10.3390/math11040816" @default.
- W4319296799 hasPublicationYear "2023" @default.
- W4319296799 type Work @default.
- W4319296799 citedByCount "3" @default.
- W4319296799 countsByYear W43192967992023 @default.
- W4319296799 crossrefType "journal-article" @default.
- W4319296799 hasAuthorship W4319296799A5025599939 @default.
- W4319296799 hasAuthorship W4319296799A5032700564 @default.
- W4319296799 hasAuthorship W4319296799A5053298425 @default.
- W4319296799 hasAuthorship W4319296799A5060520944 @default.
- W4319296799 hasAuthorship W4319296799A5061562780 @default.
- W4319296799 hasAuthorship W4319296799A5080166226 @default.
- W4319296799 hasBestOaLocation W43192967991 @default.
- W4319296799 hasConcept C104317684 @default.
- W4319296799 hasConcept C11413529 @default.
- W4319296799 hasConcept C114614502 @default.
- W4319296799 hasConcept C119599485 @default.
- W4319296799 hasConcept C127413603 @default.
- W4319296799 hasConcept C141353440 @default.
- W4319296799 hasConcept C153180895 @default.
- W4319296799 hasConcept C154945302 @default.
- W4319296799 hasConcept C155512373 @default.
- W4319296799 hasConcept C185592680 @default.
- W4319296799 hasConcept C19118579 @default.
- W4319296799 hasConcept C31972630 @default.
- W4319296799 hasConcept C33923547 @default.
- W4319296799 hasConcept C34736171 @default.
- W4319296799 hasConcept C41008148 @default.
- W4319296799 hasConcept C55493867 @default.
- W4319296799 hasConcept C63479239 @default.
- W4319296799 hasConcept C81363708 @default.
- W4319296799 hasConcept C82990744 @default.
- W4319296799 hasConcept C87619178 @default.
- W4319296799 hasConceptScore W4319296799C104317684 @default.
- W4319296799 hasConceptScore W4319296799C11413529 @default.
- W4319296799 hasConceptScore W4319296799C114614502 @default.
- W4319296799 hasConceptScore W4319296799C119599485 @default.
- W4319296799 hasConceptScore W4319296799C127413603 @default.
- W4319296799 hasConceptScore W4319296799C141353440 @default.
- W4319296799 hasConceptScore W4319296799C153180895 @default.
- W4319296799 hasConceptScore W4319296799C154945302 @default.
- W4319296799 hasConceptScore W4319296799C155512373 @default.
- W4319296799 hasConceptScore W4319296799C185592680 @default.
- W4319296799 hasConceptScore W4319296799C19118579 @default.
- W4319296799 hasConceptScore W4319296799C31972630 @default.
- W4319296799 hasConceptScore W4319296799C33923547 @default.
- W4319296799 hasConceptScore W4319296799C34736171 @default.