Emotion Transfer Using Vector-Valued Infinite Task Learning

Abstract

Style transfer is a significant problem of machine learning with numerous successful applications. In this work, we present a novel style transfer framework building upon infinite task learning and vector-valued reproducing kernel Hilbert spaces. We instantiate the idea in emotion transfer where the goal is to transform facial images to different target emotions. The proposed approach provides a principled way to gain explicit control over the continuous style space. We demonstrate the efficiency of the technique on popular facial emotion benchmarks, achieving low reconstruction cost and high emotion classification accuracy.

arXiv comment17 pages, 10 figures

References in corpus (8)

• AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• ExprGAN: Facial Expression Editing with Controllable Expression Intensity
• Learning Deep Kernels for Non-Parametric Two-Sample Tests
• Audio style transfer
• Operator-valued Kernels for Learning from Functional Response Data
• A Generalized Kernel Approach to Structured Output Learning
• Unsupervised Learning of Artistic Styles with Archetypal Style Analysis