盆栽虎皮兰专利名称:FAKECATCHER: DETECTION OF SYNTHETIC
PORTRAIT VIDEOS USING BIOLOGICAL
长千行
SIGNALS
发明人:Umur Aybars Ciftci,Ilke Demir,Lijun Yin
申请号:US17143093
申请日:20210106
公开号:US20210209388A1
汤宝如公开日:
20210708
国防手抄报专利内容由知识产权出版社提供
台湾港口
专利附图:
感恩节哪天
摘要:Detection of synthetic content in portrait videos, e.g., deep fakes, is achieved.Detectors blindly utilizing deep learning are not effective in catching fake content, as
generative models produce realistic results. However, biological signals hidden in portrait videos which are neither spatially nor temporally prerved in fake content, can be ud as implicit descriptors of authenticity. 99.39% accuracy in pairwi paration is achieved.
香蕉怎么写
A generalized classifier for fake content is formulated by analyzing signal transformations and corresponding feature ts. Signal maps are generated, and a CNN employed to improve the classifier for detecting synthetic content. Evaluation on veral datats produced superior detection rates against balines, independent of the source generator, or properties of available fake content. Experiments and evaluations include signals from various facial regions, under image distortions, with varying gment durations, from different generators, against unen datats, and under veral dimensionality reduction techniques.
申请人:Ilke Demir
香港大学研究生申请地址:Hermosa Beach CA US,Binghamton NY US
国籍:US,US
更多信息请下载全文后查看