FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313366881> ?p ?o ?g. }

• W4313366881 endingPage "340" @default.
• W4313366881 startingPage "330" @default.
• W4313366881 abstract "Abstract With the rapid development of manipulation technologies, the generation of Deep Fake videos is more accessible than ever. As a result, face forgery detection becomes a challenging task, attracting a significant amount of attention from researchers worldwide. However, most previous work, consisting of convolutional neural networks (CNN), is not sufficiently discriminative and cannot fully utilise subtle clues and similar textures during the process of facial forgery detection. Moreover, these methods cannot simultaneously consider accuracy and time efficiency. To address such problems, we propose a novel framework named FPC‐Net to extract some meaningful and unnatural expressions in local regions. This framework utilises CNN, long short‐term memory (LSTM), channel groups loss (CG‐Loss) and adaptive feature fusion to detect face forgery videos. First, the proposed method exploits spatial features by CNN, and a channel‐wise attention mechanism is employed to separate channels. Specifically, with the help of channel groups loss, the channels are divided into two groups, each representing a specific class. Second, LSTM is applied to learn the correlation of spatial features. Finally, the correlation of features is mapped into other latent spaces. Through a lot of experiments, the results are that the detection speed of the proposed method reaches 420 FPS and the auc scores achieve best performance of 99.7%, 99.9%, 94.7%, and 82.0% on Raw Celeb‐DF, Raw Face Forensics++, F2F and NT datasets respectively. The experimental results demonstrate that the proposed framework has great time efficiency performance while improving the detection performance compared with other frame‐level methods in most cases." @default.
• W4313366881 created "2023-01-06" @default.
• W4313366881 creator A5032113344 @default.
• W4313366881 creator A5037553082 @default.
• W4313366881 creator A5047062688 @default.
• W4313366881 creator A5055063396 @default.
• W4313366881 date "2022-12-30" @default.
• W4313366881 modified "2023-09-26" @default.
• W4313366881 title "FPC‐Net: Learning to detect face forgery by adaptive feature fusion of patch correlation with CG‐Loss" @default.
• W4313366881 cites W2194775991 @default.
• W4313366881 cites W2301937176 @default.
• W4313366881 cites W2786289897 @default.
• W4313366881 cites W2891145043 @default.
• W4313366881 cites W2911424785 @default.
• W4313366881 cites W2914447220 @default.
• W4313366881 cites W2942074357 @default.
• W4313366881 cites W2962958939 @default.
• W4313366881 cites W2963684180 @default.
• W4313366881 cites W2982058372 @default.
• W4313366881 cites W3034196597 @default.
• W4313366881 cites W3034552680 @default.
• W4313366881 cites W3034713808 @default.
• W4313366881 cites W3080642835 @default.
• W4313366881 cites W3169588269 @default.
• W4313366881 cites W3173317327 @default.
• W4313366881 cites W3173581984 @default.
• W4313366881 cites W3174508664 @default.
• W4313366881 cites W4214680478 @default.
• W4313366881 cites W4214691743 @default.
• W4313366881 doi "https://doi.org/10.1049/cvi2.12169" @default.
• W4313366881 hasPublicationYear "2022" @default.
• W4313366881 type Work @default.
• W4313366881 citedByCount "0" @default.
• W4313366881 crossrefType "journal-article" @default.
• W4313366881 hasAuthorship W4313366881A5032113344 @default.
• W4313366881 hasAuthorship W4313366881A5037553082 @default.
• W4313366881 hasAuthorship W4313366881A5047062688 @default.
• W4313366881 hasAuthorship W4313366881A5055063396 @default.
• W4313366881 hasBestOaLocation W43133668811 @default.
• W4313366881 hasConcept C108583219 @default.
• W4313366881 hasConcept C117220453 @default.
• W4313366881 hasConcept C119857082 @default.
• W4313366881 hasConcept C127162648 @default.
• W4313366881 hasConcept C138885662 @default.
• W4313366881 hasConcept C144024400 @default.
• W4313366881 hasConcept C153180895 @default.
• W4313366881 hasConcept C154945302 @default.
• W4313366881 hasConcept C162324750 @default.
• W4313366881 hasConcept C165696696 @default.
• W4313366881 hasConcept C187736073 @default.
• W4313366881 hasConcept C2524010 @default.
• W4313366881 hasConcept C2776401178 @default.
• W4313366881 hasConcept C2779304628 @default.
• W4313366881 hasConcept C2780451532 @default.
• W4313366881 hasConcept C31258907 @default.
• W4313366881 hasConcept C33923547 @default.
• W4313366881 hasConcept C36289849 @default.
• W4313366881 hasConcept C38652104 @default.
• W4313366881 hasConcept C41008148 @default.
• W4313366881 hasConcept C41895202 @default.
• W4313366881 hasConcept C52622490 @default.
• W4313366881 hasConcept C81363708 @default.
• W4313366881 hasConcept C97931131 @default.
• W4313366881 hasConceptScore W4313366881C108583219 @default.
• W4313366881 hasConceptScore W4313366881C117220453 @default.
• W4313366881 hasConceptScore W4313366881C119857082 @default.
• W4313366881 hasConceptScore W4313366881C127162648 @default.
• W4313366881 hasConceptScore W4313366881C138885662 @default.
• W4313366881 hasConceptScore W4313366881C144024400 @default.
• W4313366881 hasConceptScore W4313366881C153180895 @default.
• W4313366881 hasConceptScore W4313366881C154945302 @default.
• W4313366881 hasConceptScore W4313366881C162324750 @default.
• W4313366881 hasConceptScore W4313366881C165696696 @default.
• W4313366881 hasConceptScore W4313366881C187736073 @default.
• W4313366881 hasConceptScore W4313366881C2524010 @default.
• W4313366881 hasConceptScore W4313366881C2776401178 @default.
• W4313366881 hasConceptScore W4313366881C2779304628 @default.
• W4313366881 hasConceptScore W4313366881C2780451532 @default.
• W4313366881 hasConceptScore W4313366881C31258907 @default.
• W4313366881 hasConceptScore W4313366881C33923547 @default.
• W4313366881 hasConceptScore W4313366881C36289849 @default.
• W4313366881 hasConceptScore W4313366881C38652104 @default.
• W4313366881 hasConceptScore W4313366881C41008148 @default.
• W4313366881 hasConceptScore W4313366881C41895202 @default.
• W4313366881 hasConceptScore W4313366881C52622490 @default.
• W4313366881 hasConceptScore W4313366881C81363708 @default.
• W4313366881 hasConceptScore W4313366881C97931131 @default.
• W4313366881 hasFunder F4320321001 @default.
• W4313366881 hasFunder F4320321878 @default.
• W4313366881 hasIssue "3" @default.
• W4313366881 hasLocation W43133668811 @default.
• W4313366881 hasOpenAccess W4313366881 @default.
• W4313366881 hasPrimaryLocation W43133668811 @default.
• W4313366881 hasRelatedWork W2279398222 @default.
• W4313366881 hasRelatedWork W2285052147 @default.
• W4313366881 hasRelatedWork W2406522397 @default.
• W4313366881 hasRelatedWork W2725397116 @default.
• W4313366881 hasRelatedWork W2806866760 @default.

• next