Abstract: We consider the problem of zero-shot anomaly detection in which a model is pre-trained to detect anomalies in images belonging to seen classes, and expected to detect anomalies from unseen ...
The internet is absolutely overflowing with AI-generated videos, making it difficult to tell what's real. We can help you pick out the deepfakes.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback