Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection
We pre-train the HAVIC on the LRS2 dataset, which contains only real videos. Please download LRS2 here. Due to copyright we cannot release the data. We use the ...
As generative AI for development expands and becomes more commodified, it's also looking more and more like local models, not ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results