Emotion Transfer Using Vector-Valued Infinite Task Learning
This work addresses the problem of controlling continuous style space for emotion transfer in facial images, offering an incremental improvement to existing style transfer methods.
This paper introduces a novel style transfer framework based on infinite task learning and vector-valued reproducing kernel Hilbert spaces. It is applied to emotion transfer, transforming facial images to different target emotions, achieving low reconstruction cost and high emotion classification accuracy.
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.