FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200712287> ?p ?o ?g. }

• W3200712287 endingPage "123503" @default.
• W3200712287 startingPage "123493" @default.
• W3200712287 abstract "With the breakthrough of computer vision and deep learning, there has been a surge of realistic-looking fake face media manipulated by AI such as DeepFake or Face2Face that manipulate facial identities or expressions. The fake faces were mostly created for fun, but abuse has caused social unrest. For example, some celebrities have become victims of fake pornography made by DeepFake. There are also growing concerns about fake political speech videos created by Face2Face. To maintain individual privacy as well as social, political, and international security, it is imperative to develop models that detect fake faces in media. Previous research can be divided into general-purpose image forensics and face image forensics. While the former has been studied for several decades and focuses on extracting hand-crafted features of traces left in the image after manipulation, the latter is based on convolutional neural networks mainly inspired by object detection models specialized to extract images’ content features. This paper proposes a hybrid face forensics framework based on a convolutional neural network combining the two forensics approaches to enhance the manipulation detection performance. To validate the proposed framework, we used a public Face2Face dataset and a custom DeepFake dataset collected on our own. Experimental results using the two datasets showed that the proposed model is more accurate and robust at various video compression rates compared to the previous methods. Throughout class activation map visualization, the proposed framework provided information on which face parts are considered important and revealed the tempering traces invisible to naked eyes." @default.
• W3200712287 created "2021-09-27" @default.
• W3200712287 creator A5001090654 @default.
• W3200712287 creator A5017305201 @default.
• W3200712287 date "2021-01-01" @default.
• W3200712287 modified "2023-09-25" @default.
• W3200712287 title "Exposing Fake Faces Through Deep Neural Networks Combining Content and Trace Feature Extractors" @default.
• W3200712287 cites W1973629749 @default.
• W3200712287 cites W1975528596 @default.
• W3200712287 cites W1994743750 @default.
• W3200712287 cites W2000683961 @default.
• W3200712287 cites W2004068758 @default.
• W3200712287 cites W2009130368 @default.
• W3200712287 cites W2028384798 @default.
• W3200712287 cites W2045719604 @default.
• W3200712287 cites W2070484489 @default.
• W3200712287 cites W2074727269 @default.
• W3200712287 cites W2080277992 @default.
• W3200712287 cites W2083192529 @default.
• W3200712287 cites W2097117768 @default.
• W3200712287 cites W2115707751 @default.
• W3200712287 cites W2117539524 @default.
• W3200712287 cites W2118053687 @default.
• W3200712287 cites W2134396947 @default.
• W3200712287 cites W2136986582 @default.
• W3200712287 cites W2140959843 @default.
• W3200712287 cites W2146991130 @default.
• W3200712287 cites W2147885303 @default.
• W3200712287 cites W2155084545 @default.
• W3200712287 cites W2157298821 @default.
• W3200712287 cites W2158071928 @default.
• W3200712287 cites W2162156567 @default.
• W3200712287 cites W2164598857 @default.
• W3200712287 cites W2166465411 @default.
• W3200712287 cites W2183341477 @default.
• W3200712287 cites W2194775991 @default.
• W3200712287 cites W2295107390 @default.
• W3200712287 cites W2475287302 @default.
• W3200712287 cites W2477916117 @default.
• W3200712287 cites W2486034530 @default.
• W3200712287 cites W2531409750 @default.
• W3200712287 cites W2558151185 @default.
• W3200712287 cites W2603123944 @default.
• W3200712287 cites W2738406145 @default.
• W3200712287 cites W2738882920 @default.
• W3200712287 cites W2790071740 @default.
• W3200712287 cites W2798117183 @default.
• W3200712287 cites W2891145043 @default.
• W3200712287 cites W2902962850 @default.
• W3200712287 cites W2925898012 @default.
• W3200712287 cites W2962958939 @default.
• W3200712287 cites W2982058372 @default.
• W3200712287 cites W2997095758 @default.
• W3200712287 cites W3104792420 @default.
• W3200712287 cites W3145724825 @default.
• W3200712287 cites W4236231454 @default.
• W3200712287 cites W4255023712 @default.
• W3200712287 doi "https://doi.org/10.1109/access.2021.3110859" @default.
• W3200712287 hasPublicationYear "2021" @default.
• W3200712287 type Work @default.
• W3200712287 sameAs 3200712287 @default.
• W3200712287 citedByCount "4" @default.
• W3200712287 countsByYear W32007122872022 @default.
• W3200712287 crossrefType "journal-article" @default.
• W3200712287 hasAuthorship W3200712287A5001090654 @default.
• W3200712287 hasAuthorship W3200712287A5017305201 @default.
• W3200712287 hasBestOaLocation W32007122871 @default.
• W3200712287 hasConcept C134306372 @default.
• W3200712287 hasConcept C138885662 @default.
• W3200712287 hasConcept C153180895 @default.
• W3200712287 hasConcept C154945302 @default.
• W3200712287 hasConcept C2776401178 @default.
• W3200712287 hasConcept C2778152352 @default.
• W3200712287 hasConcept C2984842247 @default.
• W3200712287 hasConcept C33923547 @default.
• W3200712287 hasConcept C41008148 @default.
• W3200712287 hasConcept C41895202 @default.
• W3200712287 hasConcept C50644808 @default.
• W3200712287 hasConcept C75291252 @default.
• W3200712287 hasConceptScore W3200712287C134306372 @default.
• W3200712287 hasConceptScore W3200712287C138885662 @default.
• W3200712287 hasConceptScore W3200712287C153180895 @default.
• W3200712287 hasConceptScore W3200712287C154945302 @default.
• W3200712287 hasConceptScore W3200712287C2776401178 @default.
• W3200712287 hasConceptScore W3200712287C2778152352 @default.
• W3200712287 hasConceptScore W3200712287C2984842247 @default.
• W3200712287 hasConceptScore W3200712287C33923547 @default.
• W3200712287 hasConceptScore W3200712287C41008148 @default.
• W3200712287 hasConceptScore W3200712287C41895202 @default.
• W3200712287 hasConceptScore W3200712287C50644808 @default.
• W3200712287 hasConceptScore W3200712287C75291252 @default.
• W3200712287 hasLocation W32007122871 @default.
• W3200712287 hasLocation W32007122872 @default.
• W3200712287 hasOpenAccess W3200712287 @default.
• W3200712287 hasPrimaryLocation W32007122871 @default.
• W3200712287 hasRelatedWork W2015538044 @default.
• W3200712287 hasRelatedWork W2016461833 @default.
• W3200712287 hasRelatedWork W2052253960 @default.

• next