Deepfake has taken the world by storm, triggering a trust crisis. Current deepfake detection
methods are typically inadequate in generalizability, with a tendency to overfit to image …

We study the domain adaptation task for action recognition, namely domain adaptive action
recognition, which aims to effectively transfer action recognition power from a label-sufficient …

The malicious use and widespread dissemination of deepfake pose a significant crisis of
trust. Current deepfake detection models can generally recognize forgery images by training …

Unsupervised video domain adaptation is a practical yet challenging task. In this work, for
the first time, we tackle it from a disentanglement view. Our key idea is to handle the spatial …

Despite the progress seen in classification methods, current approaches for handling videos
with distribution shifts in source and target domains remain source-dependent as they …

We study the problem of unsupervised domain adaptation for egocentric videos. We
propose a transformer-based model to learn class-discriminative and domain-invariant …

Despite the progress seen in classification methods, current approaches for handling videos
with distribution shifts in source and target domains remain source-dependent as they …

In real-world scenarios, achieving domain adaptation and generalization poses significant
challenges, as models must adapt to or generalize across unknown target distributions …