🏢 Institute of Information Engineering, Chinese Academy of Sciences

TextCtrl: a novel diffusion-based scene text editing method using prior guidance control, achieving superior style fidelity and accuracy with a new real-world benchmark dataset, ScenePair.

SpeechForensics leverages audio-visual speech representation learning to achieve superior face forgery detection, outperforming state-of-the-art methods in cross-dataset generalization and robustness.

Unlocking superior discriminative features from diffusion models, this research reveals key activation properties for effective feature selection, surpassing state-of-the-art methods.