Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206682457> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3206682457 abstract "Recent progress in deep learning-based image generation has madeit easier to create convincing fake videos called deepfakes. Whilethe benefits of such technology are undeniable, it can also be usedas realistic fake news support for mass disinformation. In this con-test, different detectors were proposed, many of them use a CNN asa backbone model and the binary cross-entropy as a loss function.Some more recent approaches applied a triplet loss with semi-hardtriplets. In this paper, we investigate the use of triplet loss with fixedpositive and negative vectors as a replacement for semi-hard triplets.This loss, called dummy triplet loss (DmyT), follows the concept ofthe triplet loss but requires less computation, as the triplets are fixed.It also doesn't rely on a linear classifier for prediction. We haveassessed the performance of the proposed loss with four backbonenetworks, including two of the most popular CNNs in the Deepfakerealm, Xception and EfficientNet, alongside two visual transformernetworks, ViT and CaiT. Our loss function shows competitive re-sults on FaceForensics++ dataset compared to triplet loss with semi-hard triplets while being less computationally intensive. The sourcecode of DmyT is available at https://github.com/beuve/DmyT." @default.
- W3206682457 created "2021-10-25" @default.
- W3206682457 creator A5031377954 @default.
- W3206682457 creator A5038179388 @default.
- W3206682457 creator A5084205574 @default.
- W3206682457 date "2021-10-20" @default.
- W3206682457 modified "2023-09-25" @default.
- W3206682457 title "DmyT" @default.
- W3206682457 cites W2078944335 @default.
- W3206682457 cites W2486034530 @default.
- W3206682457 cites W2913399670 @default.
- W3206682457 cites W2997517962 @default.
- W3206682457 cites W3034785167 @default.
- W3206682457 cites W3092879151 @default.
- W3206682457 cites W3093077034 @default.
- W3206682457 cites W3122852338 @default.
- W3206682457 cites W3174572554 @default.
- W3206682457 doi "https://doi.org/10.1145/3476099.3484316" @default.
- W3206682457 hasPublicationYear "2021" @default.
- W3206682457 type Work @default.
- W3206682457 sameAs 3206682457 @default.
- W3206682457 citedByCount "3" @default.
- W3206682457 countsByYear W32066824572022 @default.
- W3206682457 countsByYear W32066824572023 @default.
- W3206682457 crossrefType "proceedings-article" @default.
- W3206682457 hasAuthorship W3206682457A5031377954 @default.
- W3206682457 hasAuthorship W3206682457A5038179388 @default.
- W3206682457 hasAuthorship W3206682457A5084205574 @default.
- W3206682457 hasConcept C11413529 @default.
- W3206682457 hasConcept C136764020 @default.
- W3206682457 hasConcept C14036430 @default.
- W3206682457 hasConcept C153180895 @default.
- W3206682457 hasConcept C154945302 @default.
- W3206682457 hasConcept C167981619 @default.
- W3206682457 hasConcept C2776552730 @default.
- W3206682457 hasConcept C41008148 @default.
- W3206682457 hasConcept C45374587 @default.
- W3206682457 hasConcept C518677369 @default.
- W3206682457 hasConcept C78458016 @default.
- W3206682457 hasConcept C80444323 @default.
- W3206682457 hasConcept C86803240 @default.
- W3206682457 hasConceptScore W3206682457C11413529 @default.
- W3206682457 hasConceptScore W3206682457C136764020 @default.
- W3206682457 hasConceptScore W3206682457C14036430 @default.
- W3206682457 hasConceptScore W3206682457C153180895 @default.
- W3206682457 hasConceptScore W3206682457C154945302 @default.
- W3206682457 hasConceptScore W3206682457C167981619 @default.
- W3206682457 hasConceptScore W3206682457C2776552730 @default.
- W3206682457 hasConceptScore W3206682457C41008148 @default.
- W3206682457 hasConceptScore W3206682457C45374587 @default.
- W3206682457 hasConceptScore W3206682457C518677369 @default.
- W3206682457 hasConceptScore W3206682457C78458016 @default.
- W3206682457 hasConceptScore W3206682457C80444323 @default.
- W3206682457 hasConceptScore W3206682457C86803240 @default.
- W3206682457 hasLocation W32066824571 @default.
- W3206682457 hasLocation W32066824572 @default.
- W3206682457 hasOpenAccess W3206682457 @default.
- W3206682457 hasPrimaryLocation W32066824571 @default.
- W3206682457 hasRelatedWork W1534842550 @default.
- W3206682457 hasRelatedWork W1970403310 @default.
- W3206682457 hasRelatedWork W1984227438 @default.
- W3206682457 hasRelatedWork W2033914206 @default.
- W3206682457 hasRelatedWork W2046077695 @default.
- W3206682457 hasRelatedWork W2146076056 @default.
- W3206682457 hasRelatedWork W2163831990 @default.
- W3206682457 hasRelatedWork W2354062721 @default.
- W3206682457 hasRelatedWork W3003836766 @default.
- W3206682457 hasRelatedWork W3107474891 @default.
- W3206682457 isParatext "false" @default.
- W3206682457 isRetracted "false" @default.
- W3206682457 magId "3206682457" @default.
- W3206682457 workType "article" @default.