Communication Dans Un Congrès Année : 2025

REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge

Siyang Song
Micol Spitale
Xiangyu Kong
Hengde Zhu
Cristina Palmero
Sergio Escalera
  • Fonction : Auteur
  • PersonId : 1092605
Michel Valstar
Andrew Howes

Résumé

In dyadic interactions, a broad spectrum of human facial reactions might be appropriate for responding to each human speaker behaviour. Following the successful organisation of the REACT 2023 and REACT 2024 challenges, we are proposing the REACT 2025 challenge encouraging the development and benchmarking of Machine Learning (ML) models that can be used to generate multiple appropriate, diverse, realistic and synchronised human-style facial reactions expressed by human listeners in response to an input stimulus (i.e., audio-visual behaviours expressed by their corresponding speakers). As a key of the challenge, we provide challenge participants with the first natural and large-scale multimodal Multiple Appropriate Facial Reaction Generation (MAFRG) dataset (called MARS) recording 136 human-human dyadic interactions containing a total of 2856 interaction sessions covering

Fichier principal
Vignette du fichier
REACT2025___HAL.pdf (1.72 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05430604 , version 1 (23-12-2025)

Licence

Identifiants

Citer

Siyang Song, Micol Spitale, Xiangyu Kong, Hengde Zhu, Cheng Luo, et al.. REACT 2025: the Third Multiple Appropriate Facial Reaction Generation Challenge. MM '25: The 33rd ACM International Conference on Multimedia, Oct 2025, Dublin, Ireland. pp.13979-13984, ⟨10.1145/3746027.3762244⟩. ⟨hal-05430604⟩
800 Consultations
262 Téléchargements

Altmetric

Partager

  • More