FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318777691> ?p ?o ?g. }

• W4318777691 endingPage "1887" @default.
• W4318777691 startingPage "1887" @default.
• W4318777691 abstract "With the increasing visual realism of computer-graphics (CG) images generated by advanced rendering engines, the distinction between CG images and natural images (NIs) has become an important research problem in the image forensics community. Previous research works mainly focused on the conventional supervised learning framework, which usually requires a good quantity of labeled data for training. To our knowledge, we study, for the first time in the literature, the utility of the self-supervised learning mechanism for the forensic classification of CG images and NIs. The idea is to make use of a large number of readily available unlabeled data, along with a self-supervised training procedure on a well-designed pretext task for which labels can be generated in an automatic and convenient way without human manual labeling effort. Differing from existing self-supervised methods, based on pretext tasks targeted at image understanding, or based on contrastive learning, we propose carrying out self-supervised training on a forensics-oriented pretext task of classifying authentic images and their modified versions after applying various manipulations. Experiments and comparisons showed the effectiveness of our method for solving the CG forensics problem under different evaluation scenarios. Our proposed method outperformed existing self-supervised methods in all experiments. It could sometimes achieve comparable, or better, performance. compared with a state-of-the-art fully supervised method under difficult evaluation scenarios with data scarcity and a challenging forensic problem. Our study demonstrates the utility and potential of the self-supervised learning mechanism for image forensics applications." @default.
• W4318777691 created "2023-02-02" @default.
• W4318777691 creator A5073531557 @default.
• W4318777691 date "2023-02-01" @default.
• W4318777691 modified "2023-09-25" @default.
• W4318777691 title "Self-Supervised Learning for the Distinction between Computer-Graphics Images and Natural Images" @default.
• W4318777691 cites W104847522 @default.
• W4318777691 cites W1964026338 @default.
• W4318777691 cites W1997127867 @default.
• W4318777691 cites W1998113266 @default.
• W4318777691 cites W2017674864 @default.
• W4318777691 cites W2055745001 @default.
• W4318777691 cites W2062503914 @default.
• W4318777691 cites W2095130919 @default.
• W4318777691 cites W2100124582 @default.
• W4318777691 cites W2108598243 @default.
• W4318777691 cites W2155872065 @default.
• W4318777691 cites W2194775991 @default.
• W4318777691 cites W2321533354 @default.
• W4318777691 cites W2326925005 @default.
• W4318777691 cites W2553201531 @default.
• W4318777691 cites W2762911267 @default.
• W4318777691 cites W2786289897 @default.
• W4318777691 cites W2798117183 @default.
• W4318777691 cites W2799785652 @default.
• W4318777691 cites W2883088976 @default.
• W4318777691 cites W2963720850 @default.
• W4318777691 cites W3010352349 @default.
• W4318777691 cites W3023371261 @default.
• W4318777691 cites W3034530968 @default.
• W4318777691 cites W3034558629 @default.
• W4318777691 cites W3035524453 @default.
• W4318777691 cites W3080079636 @default.
• W4318777691 cites W3082587664 @default.
• W4318777691 cites W3101649689 @default.
• W4318777691 cites W3134210100 @default.
• W4318777691 cites W3142599389 @default.
• W4318777691 cites W3204051164 @default.
• W4318777691 cites W3214554068 @default.
• W4318777691 cites W343636949 @default.
• W4318777691 cites W4200524038 @default.
• W4318777691 cites W4221108250 @default.
• W4318777691 cites W4244098250 @default.
• W4318777691 cites W4291023040 @default.
• W4318777691 cites W4307972630 @default.
• W4318777691 cites W4311137818 @default.
• W4318777691 cites W4312312750 @default.
• W4318777691 doi "https://doi.org/10.3390/app13031887" @default.
• W4318777691 hasPublicationYear "2023" @default.
• W4318777691 type Work @default.
• W4318777691 citedByCount "0" @default.
• W4318777691 crossrefType "journal-article" @default.
• W4318777691 hasAuthorship W4318777691A5073531557 @default.
• W4318777691 hasBestOaLocation W43187776911 @default.
• W4318777691 hasConcept C119857082 @default.
• W4318777691 hasConcept C136389625 @default.
• W4318777691 hasConcept C153180895 @default.
• W4318777691 hasConcept C154945302 @default.
• W4318777691 hasConcept C162324750 @default.
• W4318777691 hasConcept C17744445 @default.
• W4318777691 hasConcept C187736073 @default.
• W4318777691 hasConcept C199539241 @default.
• W4318777691 hasConcept C205711294 @default.
• W4318777691 hasConcept C2779627259 @default.
• W4318777691 hasConcept C2780451532 @default.
• W4318777691 hasConcept C41008148 @default.
• W4318777691 hasConcept C50644808 @default.
• W4318777691 hasConcept C94625758 @default.
• W4318777691 hasConceptScore W4318777691C119857082 @default.
• W4318777691 hasConceptScore W4318777691C136389625 @default.
• W4318777691 hasConceptScore W4318777691C153180895 @default.
• W4318777691 hasConceptScore W4318777691C154945302 @default.
• W4318777691 hasConceptScore W4318777691C162324750 @default.
• W4318777691 hasConceptScore W4318777691C17744445 @default.
• W4318777691 hasConceptScore W4318777691C187736073 @default.
• W4318777691 hasConceptScore W4318777691C199539241 @default.
• W4318777691 hasConceptScore W4318777691C205711294 @default.
• W4318777691 hasConceptScore W4318777691C2779627259 @default.
• W4318777691 hasConceptScore W4318777691C2780451532 @default.
• W4318777691 hasConceptScore W4318777691C41008148 @default.
• W4318777691 hasConceptScore W4318777691C50644808 @default.
• W4318777691 hasConceptScore W4318777691C94625758 @default.
• W4318777691 hasFunder F4320320883 @default.
• W4318777691 hasIssue "3" @default.
• W4318777691 hasLocation W43187776911 @default.
• W4318777691 hasLocation W43187776912 @default.
• W4318777691 hasLocation W43187776913 @default.
• W4318777691 hasOpenAccess W4318777691 @default.
• W4318777691 hasPrimaryLocation W43187776911 @default.
• W4318777691 hasRelatedWork W2953328427 @default.
• W4318777691 hasRelatedWork W2971361125 @default.
• W4318777691 hasRelatedWork W3046775127 @default.
• W4318777691 hasRelatedWork W3091943846 @default.
• W4318777691 hasRelatedWork W3094076422 @default.
• W4318777691 hasRelatedWork W3162567751 @default.
• W4318777691 hasRelatedWork W4220686584 @default.
• W4318777691 hasRelatedWork W4221088574 @default.
• W4318777691 hasRelatedWork W4285260836 @default.

• next