Continuous emotion transfer using kernels

Lambert, Alex, Parekh, Sanjeel, Szabo, Zoltan ORCID: 0000-0001-6183-7603 and d'Alché-Buc, Florence (2021) Continuous emotion transfer using kernels. In: Controllable Generative Modeling in Language and Vision: CtrlGen Workshop at NeurIPS 2021, 2021-12-13, Online.

	Text (Szabo_continuous-emotion-transfer-using-kernels--paper) - Published Version Download (1MB)
	Text (Szabo_continuous-emotion-transfer-using-kernels--poster) - Published Version Download (2MB)

• Related Item
• Author

Abstract

Style transfer is a central 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 consider style transfer as a functional output regression task where the goal is to transform the input objects to a continuum of styles. The learnt mapping is governed by the choice of two kernels, one on the object space and one on the style space, providing flexibility to the approach. We instantiate the idea in emotion transfer where facial landmarks play the role of objects and styles correspond to emotions. The proposed approach provides a principled way to gain explicit control over the continuous style space, allowing to transform landmarks to emotions not seen during the training phase. We demonstrate the efficiency of the technique on popular facial emotion benchmarks, achieving low reconstruction cost

Item Type:	Conference or Workshop Item (Paper)
Official URL:	https://ctrlgenworkshop.github.io/
Additional Information:	© 2022 The Authors
Divisions:	Statistics
Subjects:	H Social Sciences > HA Statistics
Date Deposited:	01 Aug 2022 09:21
Last Modified:	20 Dec 2024 01:00
URI:	http://eprints.lse.ac.uk/id/eprint/115686

Actions (login required)

View Item