EUVIMEDEUVIMED entdecken
Crossref

PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation

Hengde Zhu, Xiangyu Kong, Weicheng Xie, Xin Huang, Xilin He, Lu Liu, Linlin Shen, Wei Zhang, Hatice Gunes, Siyang Song

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (2) · 1665-1673

DOI: 10.1609/aaai.v39i2.32159 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Hengde Zhu und 9 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In dyadic human-human interactions, individuals may express multiple different facial reactions in response to the same/similar behaviours expressed by their conversational partners depending on their personalised behaviour patterns. As a result, frequently-employed reconstruction loss-based strategies lead the training of previous automatic facial reaction generation (FRG) models to not only suffer from the 'one-to-many mapping' problem, but also fail to comprehensively consider the quality of the generated facial reactions. Besides, none of them considered such personalised behaviour patterns in generating facial reactions. In this paper, we propose the first adversarial FRG model training strategy which jointly learns appropriateness and realism discriminators to provide comprehensive task-specific supervision for training the target facial reaction generators, and reformulates the 'one-to-many (facial reactions) mapping' training problem as a 'one-to-one (distribution) mapping' training task, i.e., the FRG model is trained to output a distribution representing multiple appropriate/plausible facial reaction from each input human behaviour. In addition, our approach also serves as the first offline FRG approach that considers personalised behaviour patterns in generating of target individuals' facial reactions. Experiments show that our PerReactor not only largely outperformed all existing offline solutions for generating more appropriate, diverse and realistic facial reactions, but also is the first approach that can effectively generate personalised appropriate facial reactions.

Zitieren

APA

Zhu, H., Kong, X., Xie, W., Huang, X., He, X., Liu, L., Shen, L., Zhang, W., Gunes, H., & Song, S. (2025). PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(2), 1665-1673. https://doi.org/10.1609/aaai.v39i2.32159

Vancouver

Zhu H, Kong X, Xie W, Huang X, He X, Liu L, et al. PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(2):1665-1673. doi:10.1609/aaai.v39i2.32159

BibTeX
@article{Zhu2025,
  author = {Zhu, Hengde and Kong, Xiangyu and Xie, Weicheng and Huang, Xin and He, Xilin and Liu, Lu and Shen, Linlin and Zhang, Wei and Gunes, Hatice and Song, Siyang},
  title = {PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {2},
  pages = {1665--1673},
  doi = {10.1609/aaai.v39i2.32159}
}
Kostenlos starten →