Search Results for author:
Found 5 papers, 3 papers with code
Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos
This allows us to link the synthetic video to the identity driving the expressions in the video, regardless of the facial appearance shown.
Generalizable Deepfake Detection with Phase-Based Motion Analysis
Overall, with PhaseForensics, we show improved distortion and adversarial robustness, and state-of-the-art cross-dataset generalization, with 91. 2% video-level AUC on the challenging CelebDFv2 (a recent state-of-the-art compares at 86. 9%).
LOCL: Learning Object-Attribute Composition using Localization
This paper describes LOCL (Learning Object Attribute Composition using Localization) that generalizes composition zero shot learning to objects in cluttered and more realistic settings.
Ranked #1 on
Zero-Shot Learning
on MIT-States
Noise-Aware Video Saliency Prediction
We note that the accuracy of the maps reconstructed from the gaze data of a fixed number of observers varies with the frame, as it depends on the content of the scene.
PieAPP: Perceptual Image-Error Assessment through Pairwise Preference
Our key observation is that our trained network can then be used separately with only one distorted image and a reference to predict its perceptual error, without ever being trained on explicit human perceptual-error labels.
Ranked #1 on
Video Quality Assessment
on MSU SR-QA Dataset
