Search Results for author: Immanuel Schweizer

Found 2 papers, 0 papers with code

Empirical Evaluation of Supervision Signals for Style Transfer Models

no code implementations15 Jan 2021 Yevgeniy Puzikov, Simoes Stanley, Iryna Gurevych, Immanuel Schweizer

In this work we empirically compare the dominant optimization paradigms which provide supervision signals during training: backtranslation, adversarial training and reinforcement learning.

Machine Translation reinforcement-learning +4

A Framework for Learning Invariant Physical Relations in Multimodal Sensory Processing

no code implementations30 Jun 2020 Du Xiaorui, Yavuzhan Erdem, Immanuel Schweizer, Cristian Axenie

We design a novel neural network architecture capable of learning, in an unsupervised manner, relations among multiple sensory cues.

Optical Flow Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.