BELMEKKI, Zakariae; GOMEZ, David; REUTER, Patrick; LI, Jun; MARTIN, Jean-Claude; JENKINS, Karl W.; COUTURE, Nadine

doi:10.1145/3678957.3685712

BELMEKKI, Zakariae
ESTIA INSTITUTE OF TECHNOLOGY

GOMEZ, David

ESTIA INSTITUTE OF TECHNOLOGY

REUTER, Patrick

Laboratoire Bordelais de Recherche en Informatique [LaBRI]
ESTIA INSTITUTE OF TECHNOLOGY

Langue

Communication dans un congrès

Ce document a été publié dans

ICMI '24: Proceedings of the 26th International Conference on Multimodal Interaction, 26th ACM International Conference on Multimodal Interaction, 2024-11-04, San Jose. p. 361-372

ACM

Résumé en anglais

There is a rising interest in animating realistic virtual agents for multiple purposes in diferent domains. Such a task requires systems capable of generating complex mental states on par with human emotional complexity. Considering the high representational capacity of Generative Adversarial Networks (GANs), it is only natural to consider them in such applications. In this work, we propose a conditional GAN model for generating sequences of facial expressions of categorical complex emotions. Trained on a scarce and highly imbalanced dataset, the proposed model is able to generate realistic variable-length sequences in a single inference step. These expressions of emotional states, of which there are 24 in total, follow the Facial Actions Coding System (FACS) formatting. In the absence of meaningful objective evaluation methods, we propose a deeplearning-based metric to assess the realism of generated Action Unit (AU) sequences: the Action Unit Fréchet Inception Distance (AUFID). Objective and subjective results validate the realism of our generated samples.< Réduire

Mots clés en anglais

Generative Adversarial Networks

Complex Emotional States

Synthetic Action Units

FACS

URI

https://oskar-bordeaux.fr/handle/20.500.12278/203961

DOI

http://dx.doi.org/10.1145/3678957.3685712

Unités de recherche

ESTIA - Recherche

Voir/Ouvrir

Métadonnées

Partager cette publication !

Licence d’utilisation du document

Generating Facial Expression Sequences of Complex Emotions with Generative Adversarial Networks

Langue

Ce document a été publié dans

Résumé en anglais

Mots clés en anglais

URI

DOI

Unités de recherche