3 papers
cs.CV2020
The benefits of synthetic data for action categorization
Mohamad Ballout, Mohammad Tuqan, Daniel Asmar +2
In this paper, we study the value of using synthetically produced videos as training data for neural networks used for action categorization. Motivated by the fact that texture and…
cs.LG2019
Change your singer: a transfer learning generative adversarial framework for song to song conversion
Rema Daher, Mohammad Kassem Zein, Julia El Zini +2
Have you ever wondered how a song might sound if performed by a different artist? In this work, we propose SCM-GAN, an end-to-end non-parallel song conversion system powered by gen…
cs.CV2019
A Unified Formulation for Visual Odometry
Georges Younes, Daniel Asmar, John Zelek
Monocular Odometry systems can be broadly categorized as being either Direct, Indirect, or a hybrid of both. While Indirect systems process an alternative image representation to c…