Search Results for author:
Found 3 papers, 1 papers with code
SIDGAN: High-Resolution Dubbed Video Generation via Shift-Invariant Learning
Dubbed video generation aims to accurately synchronize mouth movements of a given facial video with driving audio while preserving identity and scene-specific visual dynamics, such as head pose and lighting.
Transfer Learning from an Auxiliary Discriminative Task for Unsupervised Anomaly Detection
We propose use of an auxiliary classification task to extract features from unlabelled data by supervised learning, which can be used for unsupervised anomaly detection.
Reducing Gender Bias in Word-Level Language Models with a Gender-Equalizing Loss Function
Finally, we introduce a combination of data augmentation and our approach, and show that it outperforms existing strategies in all bias evaluation metrics.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
