Matches in SemOpenAlex for { <https://semopenalex.org/work/W3155334261> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3155334261 abstract "Although vanilla Convolutional Neural Network (CNN) based detectors can achieve satisfactory performance on fake face detection, we observe that the detectors tend to seek forgeries on a limited region of face, which reveals that the detectors is short of understanding of forgery. Therefore, we propose an attention-based data augmentation framework to guide detector refine and enlarge its attention. Specifically, our method tracks and occludes the Top-N sensitive facial regions, encouraging the detector to mine deeper into the regions ignored before for more representative forgery. Especially, our method is simple-to-use and can be easily integrated with various CNN models. Extensive experiments show that the detector trained with our method is capable to separately point out the representative forgery of fake faces generated by different manipulation techniques, and our method enables a vanilla CNN-based detector to achieve state-of-the-art performance without structure modification." @default.
- W3155334261 created "2021-04-26" @default.
- W3155334261 creator A5025452586 @default.
- W3155334261 creator A5046664390 @default.
- W3155334261 date "2021-04-13" @default.
- W3155334261 modified "2023-09-26" @default.
- W3155334261 title "Representative Forgery Mining for Fake Face Detection" @default.
- W3155334261 cites W2095705004 @default.
- W3155334261 cites W2115252128 @default.
- W3155334261 cites W2163605009 @default.
- W3155334261 cites W2295107390 @default.
- W3155334261 cites W2301937176 @default.
- W3155334261 cites W2531409750 @default.
- W3155334261 cites W2600144439 @default.
- W3155334261 cites W2738406145 @default.
- W3155334261 cites W2742330194 @default.
- W3155334261 cites W2746314669 @default.
- W3155334261 cites W2765793020 @default.
- W3155334261 cites W2962760235 @default.
- W3155334261 cites W2962770929 @default.
- W3155334261 cites W2962835968 @default.
- W3155334261 cites W2962858109 @default.
- W3155334261 cites W2963399829 @default.
- W3155334261 cites W2963767194 @default.
- W3155334261 cites W2964121744 @default.
- W3155334261 cites W2975558816 @default.
- W3155334261 cites W2982058372 @default.
- W3155334261 cites W2991318208 @default.
- W3155334261 cites W2998508940 @default.
- W3155334261 cites W3002979287 @default.
- W3155334261 cites W3012472557 @default.
- W3155334261 cites W3022873534 @default.
- W3155334261 cites W3034196597 @default.
- W3155334261 cites W3034301684 @default.
- W3155334261 cites W3034672614 @default.
- W3155334261 cites W3034713808 @default.
- W3155334261 cites W3034795015 @default.
- W3155334261 cites W3035063907 @default.
- W3155334261 cites W3035574324 @default.
- W3155334261 cites W3038930935 @default.
- W3155334261 cites W3108281670 @default.
- W3155334261 doi "https://doi.org/10.48550/arxiv.2104.06609" @default.
- W3155334261 hasPublicationYear "2021" @default.
- W3155334261 type Work @default.
- W3155334261 sameAs 3155334261 @default.
- W3155334261 citedByCount "0" @default.
- W3155334261 crossrefType "posted-content" @default.
- W3155334261 hasAuthorship W3155334261A5025452586 @default.
- W3155334261 hasAuthorship W3155334261A5046664390 @default.
- W3155334261 hasBestOaLocation W31553342611 @default.
- W3155334261 hasConcept C111472728 @default.
- W3155334261 hasConcept C138885662 @default.
- W3155334261 hasConcept C144024400 @default.
- W3155334261 hasConcept C153180895 @default.
- W3155334261 hasConcept C154945302 @default.
- W3155334261 hasConcept C2524010 @default.
- W3155334261 hasConcept C2779304628 @default.
- W3155334261 hasConcept C2780586882 @default.
- W3155334261 hasConcept C28719098 @default.
- W3155334261 hasConcept C31972630 @default.
- W3155334261 hasConcept C33923547 @default.
- W3155334261 hasConcept C36289849 @default.
- W3155334261 hasConcept C41008148 @default.
- W3155334261 hasConcept C76155785 @default.
- W3155334261 hasConcept C81363708 @default.
- W3155334261 hasConcept C94915269 @default.
- W3155334261 hasConceptScore W3155334261C111472728 @default.
- W3155334261 hasConceptScore W3155334261C138885662 @default.
- W3155334261 hasConceptScore W3155334261C144024400 @default.
- W3155334261 hasConceptScore W3155334261C153180895 @default.
- W3155334261 hasConceptScore W3155334261C154945302 @default.
- W3155334261 hasConceptScore W3155334261C2524010 @default.
- W3155334261 hasConceptScore W3155334261C2779304628 @default.
- W3155334261 hasConceptScore W3155334261C2780586882 @default.
- W3155334261 hasConceptScore W3155334261C28719098 @default.
- W3155334261 hasConceptScore W3155334261C31972630 @default.
- W3155334261 hasConceptScore W3155334261C33923547 @default.
- W3155334261 hasConceptScore W3155334261C36289849 @default.
- W3155334261 hasConceptScore W3155334261C41008148 @default.
- W3155334261 hasConceptScore W3155334261C76155785 @default.
- W3155334261 hasConceptScore W3155334261C81363708 @default.
- W3155334261 hasConceptScore W3155334261C94915269 @default.
- W3155334261 hasLocation W31553342611 @default.
- W3155334261 hasOpenAccess W3155334261 @default.
- W3155334261 hasPrimaryLocation W31553342611 @default.
- W3155334261 hasRelatedWork W1899364738 @default.
- W3155334261 hasRelatedWork W1955116508 @default.
- W3155334261 hasRelatedWork W2023301637 @default.
- W3155334261 hasRelatedWork W2103413230 @default.
- W3155334261 hasRelatedWork W2521062615 @default.
- W3155334261 hasRelatedWork W2908959303 @default.
- W3155334261 hasRelatedWork W2976316911 @default.
- W3155334261 hasRelatedWork W3093612317 @default.
- W3155334261 hasRelatedWork W4316658612 @default.
- W3155334261 hasRelatedWork W43171467 @default.
- W3155334261 isParatext "false" @default.
- W3155334261 isRetracted "false" @default.
- W3155334261 magId "3155334261" @default.
- W3155334261 workType "article" @default.