FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366992445> ?p ?o ?g. }

• W4366992445 endingPage "104686" @default.
• W4366992445 startingPage "104686" @default.
• W4366992445 abstract "Synthesizing videos with forged faces is a fundamental yet important safety-critical task that has caused severe security issues in recent years. Although many existing face forgery detection methods have achieved superior performance on such synthetic videos, they are severely limited by the domain-specific training data and generally perform unsatisfied when transferred to the cross-dataset scenario due to the domain gaps. Based on this observation, in this paper, we propose a multi-level feature disentanglement network to be robust to this domain bias induced by the different types of fake artifacts in different datasets. Specifically, we first detect the face image and transform it into both color-aware and frequency-aware inputs for multi-modal contextual representation learning. Then, we introduce a novel feature disentangling module that mainly utilizes a pair of complementary attention maps, to disentangle the synthetic features into separate realistic features and the features of fake artifacts. Since the features of fake artifacts are indirectly obtained from the latent features instead of the dataset-specific distribution, our forgery detection model is robust to the dataset-specific domain gaps. By applying the disentangling module to multi-levels of the feature extraction network with multi-modal inputs, we can obtain more robust feature representations. In addition, a realistic-aware adversary loss and a domain-aware adversary loss are adopted to facilitate the network for better feature disentanglement and extraction. Extensive experiments on four datasets verify the generalization of our method and present the state-of-the-art performance." @default.
• W4366992445 created "2023-04-27" @default.
• W4366992445 creator A5008417257 @default.
• W4366992445 creator A5032015275 @default.
• W4366992445 creator A5038413429 @default.
• W4366992445 creator A5047459900 @default.
• W4366992445 creator A5058611515 @default.
• W4366992445 creator A5065871371 @default.
• W4366992445 creator A5078220957 @default.
• W4366992445 date "2023-07-01" @default.
• W4366992445 modified "2023-09-26" @default.
• W4366992445 title "Multi-level feature disentanglement network for cross-dataset face forgery detection" @default.
• W4366992445 cites W2009130368 @default.
• W4366992445 cites W2284800790 @default.
• W4366992445 cites W2766623491 @default.
• W4366992445 cites W2942074357 @default.
• W4366992445 cites W3098883884 @default.
• W4366992445 cites W3131890248 @default.
• W4366992445 cites W3142806976 @default.
• W4366992445 cites W4205817612 @default.
• W4366992445 doi "https://doi.org/10.1016/j.imavis.2023.104686" @default.
• W4366992445 hasPublicationYear "2023" @default.
• W4366992445 type Work @default.
• W4366992445 citedByCount "0" @default.
• W4366992445 crossrefType "journal-article" @default.
• W4366992445 hasAuthorship W4366992445A5008417257 @default.
• W4366992445 hasAuthorship W4366992445A5032015275 @default.
• W4366992445 hasAuthorship W4366992445A5038413429 @default.
• W4366992445 hasAuthorship W4366992445A5047459900 @default.
• W4366992445 hasAuthorship W4366992445A5058611515 @default.
• W4366992445 hasAuthorship W4366992445A5065871371 @default.
• W4366992445 hasAuthorship W4366992445A5078220957 @default.
• W4366992445 hasConcept C119857082 @default.
• W4366992445 hasConcept C124101348 @default.
• W4366992445 hasConcept C134306372 @default.
• W4366992445 hasConcept C138885662 @default.
• W4366992445 hasConcept C144024400 @default.
• W4366992445 hasConcept C153180895 @default.
• W4366992445 hasConcept C154945302 @default.
• W4366992445 hasConcept C162324750 @default.
• W4366992445 hasConcept C177148314 @default.
• W4366992445 hasConcept C17744445 @default.
• W4366992445 hasConcept C185592680 @default.
• W4366992445 hasConcept C187736073 @default.
• W4366992445 hasConcept C188027245 @default.
• W4366992445 hasConcept C199539241 @default.
• W4366992445 hasConcept C2776359362 @default.
• W4366992445 hasConcept C2776401178 @default.
• W4366992445 hasConcept C2779304628 @default.
• W4366992445 hasConcept C2780451532 @default.
• W4366992445 hasConcept C33923547 @default.
• W4366992445 hasConcept C36289849 @default.
• W4366992445 hasConcept C36503486 @default.
• W4366992445 hasConcept C41008148 @default.
• W4366992445 hasConcept C41895202 @default.
• W4366992445 hasConcept C52622490 @default.
• W4366992445 hasConcept C59404180 @default.
• W4366992445 hasConcept C71139939 @default.
• W4366992445 hasConcept C94625758 @default.
• W4366992445 hasConceptScore W4366992445C119857082 @default.
• W4366992445 hasConceptScore W4366992445C124101348 @default.
• W4366992445 hasConceptScore W4366992445C134306372 @default.
• W4366992445 hasConceptScore W4366992445C138885662 @default.
• W4366992445 hasConceptScore W4366992445C144024400 @default.
• W4366992445 hasConceptScore W4366992445C153180895 @default.
• W4366992445 hasConceptScore W4366992445C154945302 @default.
• W4366992445 hasConceptScore W4366992445C162324750 @default.
• W4366992445 hasConceptScore W4366992445C177148314 @default.
• W4366992445 hasConceptScore W4366992445C17744445 @default.
• W4366992445 hasConceptScore W4366992445C185592680 @default.
• W4366992445 hasConceptScore W4366992445C187736073 @default.
• W4366992445 hasConceptScore W4366992445C188027245 @default.
• W4366992445 hasConceptScore W4366992445C199539241 @default.
• W4366992445 hasConceptScore W4366992445C2776359362 @default.
• W4366992445 hasConceptScore W4366992445C2776401178 @default.
• W4366992445 hasConceptScore W4366992445C2779304628 @default.
• W4366992445 hasConceptScore W4366992445C2780451532 @default.
• W4366992445 hasConceptScore W4366992445C33923547 @default.
• W4366992445 hasConceptScore W4366992445C36289849 @default.
• W4366992445 hasConceptScore W4366992445C36503486 @default.
• W4366992445 hasConceptScore W4366992445C41008148 @default.
• W4366992445 hasConceptScore W4366992445C41895202 @default.
• W4366992445 hasConceptScore W4366992445C52622490 @default.
• W4366992445 hasConceptScore W4366992445C59404180 @default.
• W4366992445 hasConceptScore W4366992445C71139939 @default.
• W4366992445 hasConceptScore W4366992445C94625758 @default.
• W4366992445 hasLocation W43669924451 @default.
• W4366992445 hasOpenAccess W4366992445 @default.
• W4366992445 hasPrimaryLocation W43669924451 @default.
• W4366992445 hasRelatedWork W1775397219 @default.
• W4366992445 hasRelatedWork W2001391903 @default.
• W4366992445 hasRelatedWork W2016461833 @default.
• W4366992445 hasRelatedWork W2017517155 @default.
• W4366992445 hasRelatedWork W2031420897 @default.
• W4366992445 hasRelatedWork W2353697322 @default.
• W4366992445 hasRelatedWork W2546942002 @default.
• W4366992445 hasRelatedWork W2624266381 @default.
• W4366992445 hasRelatedWork W3021189487 @default.

• next