Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386952783> ?p ?o ?g. }
- W4386952783 abstract "Nowadays, forgery faces pose pressing security concerns over fake news, fraud, impersonation, etc. Despite the demonstrated success in intra-domain face forgery detection, existing detection methods lack generalization capability and tend to suffer from dramatic performance drops when deployed to unforeseen domains. To mitigate this issue, this paper designs a more general fake face detection model based on the vision transformer(ViT) architecture. In the training phase, the pretrained ViT weights are freezed, and only the Low-Rank Adaptation(LoRA) modules are updated. Additionally, the Single Center Loss(SCL) is applied to supervise the training process, further improving the generalization capability of the model. The proposed method achieves state-of-the-arts detection performances in both cross-manipulation and cross-dataset evaluations." @default.
- W4386952783 created "2023-09-23" @default.
- W4386952783 creator A5040091210 @default.
- W4386952783 creator A5042401810 @default.
- W4386952783 creator A5058765046 @default.
- W4386952783 date "2023-08-01" @default.
- W4386952783 modified "2023-09-27" @default.
- W4386952783 title "Enhancing General Face Forgery Detection via Vision Transformer with Low-Rank Adaptation" @default.
- W4386952783 cites W2194775991 @default.
- W4386952783 cites W2486034530 @default.
- W4386952783 cites W2531409750 @default.
- W4386952783 cites W2914447220 @default.
- W4386952783 cites W2942074357 @default.
- W4386952783 cites W2963043696 @default.
- W4386952783 cites W2963684180 @default.
- W4386952783 cites W2982058372 @default.
- W4386952783 cites W3034196597 @default.
- W4386952783 cites W3034713808 @default.
- W4386952783 cites W3035063907 @default.
- W4386952783 cites W3083246145 @default.
- W4386952783 cites W3086519949 @default.
- W4386952783 cites W3094728142 @default.
- W4386952783 cites W3108854358 @default.
- W4386952783 cites W3128490151 @default.
- W4386952783 cites W3173317327 @default.
- W4386952783 cites W3174656926 @default.
- W4386952783 cites W3183999072 @default.
- W4386952783 cites W3207485660 @default.
- W4386952783 cites W4214691743 @default.
- W4386952783 cites W4280544425 @default.
- W4386952783 cites W4287080402 @default.
- W4386952783 cites W4293370654 @default.
- W4386952783 cites W4312388562 @default.
- W4386952783 cites W4312651322 @default.
- W4386952783 cites W4313022653 @default.
- W4386952783 cites W4386083143 @default.
- W4386952783 doi "https://doi.org/10.1109/mipr59079.2023.00033" @default.
- W4386952783 hasPublicationYear "2023" @default.
- W4386952783 type Work @default.
- W4386952783 citedByCount "0" @default.
- W4386952783 crossrefType "proceedings-article" @default.
- W4386952783 hasAuthorship W4386952783A5040091210 @default.
- W4386952783 hasAuthorship W4386952783A5042401810 @default.
- W4386952783 hasAuthorship W4386952783A5058765046 @default.
- W4386952783 hasConcept C119599485 @default.
- W4386952783 hasConcept C119857082 @default.
- W4386952783 hasConcept C123657996 @default.
- W4386952783 hasConcept C127413603 @default.
- W4386952783 hasConcept C134306372 @default.
- W4386952783 hasConcept C142362112 @default.
- W4386952783 hasConcept C144024400 @default.
- W4386952783 hasConcept C153180895 @default.
- W4386952783 hasConcept C153349607 @default.
- W4386952783 hasConcept C154945302 @default.
- W4386952783 hasConcept C165801399 @default.
- W4386952783 hasConcept C177148314 @default.
- W4386952783 hasConcept C2776434776 @default.
- W4386952783 hasConcept C2779304628 @default.
- W4386952783 hasConcept C31510193 @default.
- W4386952783 hasConcept C31972630 @default.
- W4386952783 hasConcept C33923547 @default.
- W4386952783 hasConcept C36289849 @default.
- W4386952783 hasConcept C38652104 @default.
- W4386952783 hasConcept C41008148 @default.
- W4386952783 hasConcept C4641261 @default.
- W4386952783 hasConcept C66322947 @default.
- W4386952783 hasConcept C95623464 @default.
- W4386952783 hasConceptScore W4386952783C119599485 @default.
- W4386952783 hasConceptScore W4386952783C119857082 @default.
- W4386952783 hasConceptScore W4386952783C123657996 @default.
- W4386952783 hasConceptScore W4386952783C127413603 @default.
- W4386952783 hasConceptScore W4386952783C134306372 @default.
- W4386952783 hasConceptScore W4386952783C142362112 @default.
- W4386952783 hasConceptScore W4386952783C144024400 @default.
- W4386952783 hasConceptScore W4386952783C153180895 @default.
- W4386952783 hasConceptScore W4386952783C153349607 @default.
- W4386952783 hasConceptScore W4386952783C154945302 @default.
- W4386952783 hasConceptScore W4386952783C165801399 @default.
- W4386952783 hasConceptScore W4386952783C177148314 @default.
- W4386952783 hasConceptScore W4386952783C2776434776 @default.
- W4386952783 hasConceptScore W4386952783C2779304628 @default.
- W4386952783 hasConceptScore W4386952783C31510193 @default.
- W4386952783 hasConceptScore W4386952783C31972630 @default.
- W4386952783 hasConceptScore W4386952783C33923547 @default.
- W4386952783 hasConceptScore W4386952783C36289849 @default.
- W4386952783 hasConceptScore W4386952783C38652104 @default.
- W4386952783 hasConceptScore W4386952783C41008148 @default.
- W4386952783 hasConceptScore W4386952783C4641261 @default.
- W4386952783 hasConceptScore W4386952783C66322947 @default.
- W4386952783 hasConceptScore W4386952783C95623464 @default.
- W4386952783 hasLocation W43869527831 @default.
- W4386952783 hasOpenAccess W4386952783 @default.
- W4386952783 hasPrimaryLocation W43869527831 @default.
- W4386952783 hasRelatedWork W1520317218 @default.
- W4386952783 hasRelatedWork W1589930024 @default.
- W4386952783 hasRelatedWork W2104399424 @default.
- W4386952783 hasRelatedWork W2150574012 @default.
- W4386952783 hasRelatedWork W2234765641 @default.
- W4386952783 hasRelatedWork W2347601237 @default.
- W4386952783 hasRelatedWork W2897995864 @default.