no code implementations • 12 Jun 2023 • Sayantan Das, Mojtaba Kolahdouzi, Levent Özparlak, Will Hickie, Ali Etemad
We present a novel approach for the detection of deepfake videos using a pair of vision transformers pre-trained by a self-supervised masked autoencoding setup.
no code implementations • NeurIPS Workshop TDA_and_Beyond 2020 • Adrish Dey, Sayantan Das
This work studies disconnected manifold learning in generative models in the light of point-set topology and persistent homology.