Matches in SemOpenAlex for { <https://semopenalex.org/work/W3011069884> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3011069884 abstract "With the arrival of several face-swapping applications such as FaceApp, SnapChat, MixBooth, FaceBlender and many more, the authenticity of digital media content is hanging on a very loose thread. On social media platforms, videos are widely circulated often at a high compression factor. In this work, we analyze several deep learning approaches in the context of deepfakes classification in high compression scenario and demonstrate that a proposed approach based on metric learning can be very effective in performing such a classification. Using less number of frames per video to assess its realism, the metric learning approach using a triplet network architecture proves to be fruitful. It learns to enhance the feature space distance between the cluster of real and fake videos embedding vectors. We validated our approaches on two datasets to analyze the behavior in different environments. We achieved a state-of-the-art AUC score of 99.2% on the Celeb-DF dataset and accuracy of 90.71% on a highly compressed Neural Texture dataset. Our approach is especially helpful on social media platforms where data compression is inevitable." @default.
- W3011069884 created "2020-03-23" @default.
- W3011069884 creator A5018647189 @default.
- W3011069884 creator A5076463582 @default.
- W3011069884 date "2020-03-19" @default.
- W3011069884 modified "2023-09-28" @default.
- W3011069884 title "Detecting Deepfakes with Metric Learning" @default.
- W3011069884 cites W2009130368 @default.
- W3011069884 cites W2412509443 @default.
- W3011069884 cites W2531409750 @default.
- W3011069884 cites W2603123944 @default.
- W3011069884 cites W2786289897 @default.
- W3011069884 cites W2891145043 @default.
- W3011069884 cites W2903382683 @default.
- W3011069884 cites W2906447902 @default.
- W3011069884 cites W2912336782 @default.
- W3011069884 cites W2942074357 @default.
- W3011069884 cites W2976451995 @default.
- W3011069884 cites W2976627522 @default.
- W3011069884 cites W2984700035 @default.
- W3011069884 cites W2998718632 @default.
- W3011069884 cites W3011288915 @default.
- W3011069884 cites W3034530968 @default.
- W3011069884 cites W3101998545 @default.
- W3011069884 hasPublicationYear "2020" @default.
- W3011069884 type Work @default.
- W3011069884 sameAs 3011069884 @default.
- W3011069884 citedByCount "1" @default.
- W3011069884 countsByYear W30110698842020 @default.
- W3011069884 crossrefType "posted-content" @default.
- W3011069884 hasAuthorship W3011069884A5018647189 @default.
- W3011069884 hasAuthorship W3011069884A5076463582 @default.
- W3011069884 hasConcept C119857082 @default.
- W3011069884 hasConcept C136764020 @default.
- W3011069884 hasConcept C153180895 @default.
- W3011069884 hasConcept C154945302 @default.
- W3011069884 hasConcept C162324750 @default.
- W3011069884 hasConcept C176217482 @default.
- W3011069884 hasConcept C21547014 @default.
- W3011069884 hasConcept C41008148 @default.
- W3011069884 hasConcept C41608201 @default.
- W3011069884 hasConcept C518677369 @default.
- W3011069884 hasConceptScore W3011069884C119857082 @default.
- W3011069884 hasConceptScore W3011069884C136764020 @default.
- W3011069884 hasConceptScore W3011069884C153180895 @default.
- W3011069884 hasConceptScore W3011069884C154945302 @default.
- W3011069884 hasConceptScore W3011069884C162324750 @default.
- W3011069884 hasConceptScore W3011069884C176217482 @default.
- W3011069884 hasConceptScore W3011069884C21547014 @default.
- W3011069884 hasConceptScore W3011069884C41008148 @default.
- W3011069884 hasConceptScore W3011069884C41608201 @default.
- W3011069884 hasConceptScore W3011069884C518677369 @default.
- W3011069884 hasLocation W30110698841 @default.
- W3011069884 hasOpenAccess W3011069884 @default.
- W3011069884 hasPrimaryLocation W30110698841 @default.
- W3011069884 hasRelatedWork W116204763 @default.
- W3011069884 hasRelatedWork W2073807451 @default.
- W3011069884 hasRelatedWork W2139349101 @default.
- W3011069884 hasRelatedWork W2609450835 @default.
- W3011069884 hasRelatedWork W2793756304 @default.
- W3011069884 hasRelatedWork W2866912866 @default.
- W3011069884 hasRelatedWork W2903034054 @default.
- W3011069884 hasRelatedWork W2909000493 @default.
- W3011069884 hasRelatedWork W2911757592 @default.
- W3011069884 hasRelatedWork W2929293193 @default.
- W3011069884 hasRelatedWork W2951890161 @default.
- W3011069884 hasRelatedWork W2978433739 @default.
- W3011069884 hasRelatedWork W3013624357 @default.
- W3011069884 hasRelatedWork W3024012329 @default.
- W3011069884 hasRelatedWork W3035089009 @default.
- W3011069884 hasRelatedWork W3093278324 @default.
- W3011069884 hasRelatedWork W3188008942 @default.
- W3011069884 hasRelatedWork W3191973200 @default.
- W3011069884 hasRelatedWork W978857790 @default.
- W3011069884 hasRelatedWork W3083866628 @default.
- W3011069884 isParatext "false" @default.
- W3011069884 isRetracted "false" @default.
- W3011069884 magId "3011069884" @default.
- W3011069884 workType "article" @default.