GANmut: learning interpretable conditional space for a gamut of emotions
GANmut: learning interpretable conditional space for a gamut of emotions
Humans can communicate emotions through a plethora of facial expressions, each with its own intensity, nuances and ambiguities. The generation of such variety by means of conditional GANs is limited to the expressions encoded in the used label system. These limitations are caused either due to burdensome labelling demand or the confounded label space. On the other hand, learning from inexpensive and intuitive basic categorical emotion labels leads to limited emotion variability. In this paper, we propose a novel GAN-based framework that learns an expressive and interpretable conditional space (usable as a label space) of emotions, instead of conditioning on handcrafted labels. Our framework only uses the categorical labels of basic emotions to learn jointly the conditional space as well as emotion manipulation. Such learning can benefit from the image variability within discrete labels, especially when the intrinsic labels reside beyond the discrete space of the defined. Our experiments demonstrate the effectiveness of the proposed framework, by allowing us to control and generate a gamut of complex and compound emotions while using only the basic categorical emotion labels during training. Our source code is available at https://github.com/stefanodapolito/GANmut.
568-577
D'Apolito, Stefano
d2e8d5cd-f79d-4f29-beca-cf680e2bb906
Paudel, Danda Pani
92cefdf8-92e7-43ff-b952-6290a9844be0
Huang, Zhiwu
84f477cd-9097-44dd-a33e-ff71f253d36b
Vergara, Andres Romero
06431161-b4d2-4ca1-95ec-8229e77f2480
Van Gool, Luc
4d5f6fcf-2814-45d4-9028-86378b4b76b7
19 June 2021
D'Apolito, Stefano
d2e8d5cd-f79d-4f29-beca-cf680e2bb906
Paudel, Danda Pani
92cefdf8-92e7-43ff-b952-6290a9844be0
Huang, Zhiwu
84f477cd-9097-44dd-a33e-ff71f253d36b
Vergara, Andres Romero
06431161-b4d2-4ca1-95ec-8229e77f2480
Van Gool, Luc
4d5f6fcf-2814-45d4-9028-86378b4b76b7
D'Apolito, Stefano, Paudel, Danda Pani, Huang, Zhiwu, Vergara, Andres Romero and Van Gool, Luc
(2021)
GANmut: learning interpretable conditional space for a gamut of emotions.
In IEEE/CVF Conference on Computer Vision and Pattern Recognition.
.
(doi:10.1109/CVPR46437.2021.00063).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Humans can communicate emotions through a plethora of facial expressions, each with its own intensity, nuances and ambiguities. The generation of such variety by means of conditional GANs is limited to the expressions encoded in the used label system. These limitations are caused either due to burdensome labelling demand or the confounded label space. On the other hand, learning from inexpensive and intuitive basic categorical emotion labels leads to limited emotion variability. In this paper, we propose a novel GAN-based framework that learns an expressive and interpretable conditional space (usable as a label space) of emotions, instead of conditioning on handcrafted labels. Our framework only uses the categorical labels of basic emotions to learn jointly the conditional space as well as emotion manipulation. Such learning can benefit from the image variability within discrete labels, especially when the intrinsic labels reside beyond the discrete space of the defined. Our experiments demonstrate the effectiveness of the proposed framework, by allowing us to control and generate a gamut of complex and compound emotions while using only the basic categorical emotion labels during training. Our source code is available at https://github.com/stefanodapolito/GANmut.
This record has no associated files available for download.
More information
Published date: 19 June 2021
Identifiers
Local EPrints ID: 501679
URI: http://eprints.soton.ac.uk/id/eprint/501679
PURE UUID: 8dd9f7d4-c920-4d8f-9fc3-0c62ac16fc3b
Catalogue record
Date deposited: 05 Jun 2025 16:57
Last modified: 06 Jun 2025 02:06
Export record
Altmetrics
Contributors
Author:
Stefano D'Apolito
Author:
Danda Pani Paudel
Author:
Zhiwu Huang
Author:
Andres Romero Vergara
Author:
Luc Van Gool
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics